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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .putString
    -0.07
     Bad
    -0.07
     Ли
    -0.07
     improbable
    -0.06
     bufsize
    -0.06
     Gaz
    -0.06
     invis
    -0.06
    (QStringLiteral
    -0.06
    학년
    -0.06
    .sb
    -0.06
    POSITIVE LOGITS
     tense
    0.06
     anniversary
    0.06
     베스트
    0.06
    OTION
    0.06
     lance
    0.06
    yyvsp
    0.06
    .Amount
    0.06
    -buttons
    0.06
    .BatchNorm
    0.06
     NSW
    0.06
    Act Density 0.015%

    No Known Activations