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

    Neuronpedia

    INDEX
    Explanations

    HTML paragraph tags that end a block of text

    oai_token-act-pair · gemini-2.0-flash

    p

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awtextra
    -0.79
    UrlResolution
    -0.71
    oredCriteria
    -0.70
     дописавши
    -0.69
    []){
    -0.67
    awaiter
    -0.66
    jsii
    -0.65
    iNdEx
    -0.65
    évaluateur
    -0.64
    oa̍t
    -0.64
    POSITIVE LOGITS
     tra
    0.43
     mac
    0.42
    tées
    0.42
     dem
    0.39
     <=>
    0.38
     đích
    0.38
     accro
    0.38
    activ
    0.38
    emm
    0.37
    totta
    0.36
    Act Density 0.557%

    No Known Activations