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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensual
    -0.07
     être
    -0.07
    picable
    -0.07
    ([]*
    -0.07
     امام
    -0.06
    _sock
    -0.06
     Kann
    -0.06
     gelmiş
    -0.06
     최근
    -0.06
    noch
    -0.06
    POSITIVE LOGITS
    -existing
    0.07
    file
    0.07
    .charAt
    0.06
     hesitant
    0.06
     guests
    0.06
     tracing
    0.06
    ceph
    0.06
    default
    0.06
    ổi
    0.06
    RV
    0.06
    Act Density 0.004%

    No Known Activations