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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بعد
    -0.07
    erv
    -0.07
    encode
    -0.07
    iciary
    -0.07
    .center
    -0.07
     jihadist
    -0.07
    极致
    -0.07
     lavender
    -0.07
    ONE
    -0.06
    _sql
    -0.06
    POSITIVE LOGITS
     прод
    0.07
     Ни
    0.07
    -law
    0.07
    切成
    0.06
    عل
    0.06
    utral
    0.06
     exclaimed
    0.06
    \Repositories
    0.06
     Leisure
    0.06
    represent
    0.06
    Act Density 0.002%

    No Known Activations