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

    Neuronpedia

    INDEX
    Explanations

    words related to positive recommendations and reviews

    oai_token-act-pair · gemini-2.0-flash

    Recommending media

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theſe
    -0.94
     myſelf
    -0.90
     Monfieur
    -0.89
     Jefus
    -0.88
    MigrationBuilder
    -0.84
    EndInit
    -0.83
    __(/*!
    -0.83
     raiſ
    -0.80
     ModelExpression
    -0.79
    NameInMap
    -0.78
    POSITIVE LOGITS
     multitud
    0.51
    ու
    0.41
     !
    0.41
     ir
    0.40
     de
    0.40
    <eos>
    0.39
     követ
    0.37
     g
    0.36
    าง
    0.36
    .
    0.36
    Act Density 1.357%

    No Known Activations