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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to numerical data and scientific trends

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

    ending in "ic", "al", "ed", "ent", or "ous"

    np_acts-logits-general · gemini-2.0-flash

    suffixes and descriptive states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.58
    AutoField
    -0.55
    ::$_
    -0.47
    kinds
    -0.47
    DeleteCommand
    -0.46
    aarrggbb
    -0.46
     saith
    -0.45
     produttore
    -0.45
    '
    -0.44
     bacio
    -0.44
    POSITIVE LOGITS
    ness
    0.83
    neſs
    0.81
    NESS
    0.72
     ness
    0.71
    DockStyle
    0.71
     status
    0.70
    휀
    0.68
    enschap
    0.68
     itſelf
    0.68
     <<<<<<<<<<<<<<
    0.67
    Act Density 0.796%

    No Known Activations