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
    次数
    -0.07
    西省
    -0.07
    UBLISH
    -0.06
    čast
    -0.06
    cej
    -0.06
    کنان
    -0.06
     cavalry
    -0.06
     конца
    -0.06
     cuis
    -0.06
     кораб
    -0.06
    POSITIVE LOGITS
    55
    0.07
    755
    0.06
    Assignable
    0.06
    snapshot
    0.06
     diagrams
    0.06
    igrationBuilder
    0.06
    164
    0.06
    .Secret
    0.06
     reflective
    0.06
    angular
    0.06
    Act Density 0.000%

    No Known Activations