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

    Neuronpedia

    INDEX
    Explanations

    HTML attributes and their values

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

    HTML structure tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.84
     ainfi
    -0.78
    ſelf
    -0.74
    ſelves
    -0.72
     ſche
    -0.71
     auroit
    -0.69
    Chham
    -0.69
    parsedMessage
    -0.68
     vectorielles
    -0.68
    ientras
    -0.67
    POSITIVE LOGITS
     "
    0.64
    ="
    0.63
     “
    0.48
     $(".
    0.46
    /
    0.45
    .
    0.44
     fig
    0.43
    -
    0.43
     (
    0.43
     The
    0.43
    Act Density 0.005%

    No Known Activations