Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    complex discussions that suggest in-depth analysis and multiple complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Omitted or detailed information

    np_acts-logits-general · gemini-2.0-flash

    presenting briefly or deferring details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.80
    +#+#
    -0.77
    ConstraintMaker
    -0.77
    WithIOException
    -0.71
    tvguidetime
    -0.69
     Wicidata
    -0.68
    aarrggbb
    -0.65
     autorytatywna
    -0.64
     resourceCulture
    -0.64
    enterOuterAlt
    -0.64
    POSITIVE LOGITS
     Suff
    0.82
    Suff
    0.65
     suffice
    0.61
     details
    0.59
     detailed
    0.58
    detailed
    0.57
     Briefly
    0.56
     intricacies
    0.56
    Details
    0.55
    details
    0.55
    Act Density 0.430%

    No Known Activations