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

    Neuronpedia

    INDEX
    Explanations

    configuration settings and parameters in code

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

    Values assigned to variables

    np_acts-logits-general · gemini-2.0-flash

    quoted string values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $")
    -0.58
    =#{
    -0.55
    $",
    -0.53
    _',
    -0.52
     =",
    -0.51
    )")
    -0.51
    SequentialGroup
    -0.51
    )");
    -0.50
    :")
    -0.50
    %")
    -0.50
    POSITIVE LOGITS
     Roskov
    0.73
    ///</
    0.69
    ../
    0.63
    ualitas
    0.61
     Visser
    0.58
    none
    0.57
    apimachinery
    0.57
    sidemargin
    0.56
     protoimpl
    0.55
     Batteries
    0.55
    Act Density 0.406%

    No Known Activations