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

    Neuronpedia

    INDEX
    Explanations

    hypothetical statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rent
    -0.06
    antom
    -0.06
    Pub
    -0.06
     emple
    -0.06
     cutoff
    -0.06
     Punk
    -0.06
    ELCOME
    -0.06
     ổn
    -0.06
     pemb
    -0.06
     measurements
    -0.06
    POSITIVE LOGITS
     кип
    0.06
    /button
    0.06
    lix
    0.06
    .getAccount
    0.06
     Stripe
    0.06
     bore
    0.06
    _mex
    0.06
    ΙΟΥ
    0.06
    ンス
    0.06
    _true
    0.06
    Act Density 0.006%

    No Known Activations