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

    Neuronpedia

    INDEX
    Explanations

    symbols or special characters, particularly the asterisk

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

    Text surrounded by asterisks

    np_acts-logits-general · gemini-2.0-flash

    legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BagLayout
    -0.82
     فريبيس
    -0.81
    Bronnen
    -0.75
     GenerationType
    -0.68
    CrossRef
    -0.68
    tagHelperRunner
    -0.68
    THISDAY
    -0.67
     validamos
    -0.67
     esternos
    -0.67
    Viited
    -0.66
    POSITIVE LOGITS
     *
    0.95
    //*
    0.91
     }^{*}$
    0.87
    *]
    0.75
     The
    0.74
     *=
    0.70
     $*$
    0.69
    ()*
    0.68
     •
    0.68
    }*
    0.67
    Act Density 0.032%

    No Known Activations