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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    str
    -0.07
    ываются
    -0.07
    ramid
    -0.07
    دان
    -0.07
    CustomerId
    -0.06
    τεί
    -0.06
     estimating
    -0.06
    datas
    -0.06
    川
    -0.06
    liest
    -0.06
    POSITIVE LOGITS
     mechanism
    0.06
     pepp
    0.06
     الن
    0.06
    _RUN
    0.06
    -framework
    0.06
     Maj
    0.06
     DECL
    0.06
     xxxx
    0.06
     helps
    0.06
    立刻
    0.05
    Act Density 0.034%

    No Known Activations