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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the asterisk character used for annotations or comments in code

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

    programming documentation context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.93
    fromnode
    -0.87
    transQ
    -0.85
     AspNetCore
    -0.77
     betweenstory
    -0.75
    principalTable
    -0.75
    tvguidetime
    -0.74
    iffance
    -0.73
     sánchez
    -0.72
     indígen
    -0.72
    POSITIVE LOGITS
    *
    0.86
     *
    0.77
    ///
    0.71
     the
    0.70
    //
    0.62
    /*
    0.59
    #
    0.59
    The
    0.54
    //*
    0.53
     
    0.52
    Act Density 0.004%

    No Known Activations