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

    Neuronpedia

    INDEX
    Explanations

    numerical values or identifiers in the text

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

    Mathematical or symbolic expressions

    np_acts-logits-general · gemini-2.0-flash

    vertical bar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -1.00
    canestro
    -0.72
    '},
    -0.69
    ".
    -0.69
     greateſt
    -0.69
    %")
    -0.65
     purpoſe
    -0.64
     Instrumentation
    -0.64
    consulté
    -0.64
    ItemBackground
    -0.63
    POSITIVE LOGITS
     |
    1.42
    |
    1.27
     $|
    0.73
     "|
    0.65
     autorytatywna
    0.65
    .|
    0.64
    |"
    0.56
     '|
    0.56
    ("|
    0.55
    |()
    0.54
    Act Density 0.164%

    No Known Activations