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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eil
    -0.06
    па
    -0.06
     realm
    -0.06
     труда
    -0.06
     knee
    -0.06
    /ml
    -0.06
    _pa
    -0.06
     amps
    -0.06
     lifecycle
    -0.06
     egreg
    -0.06
    POSITIVE LOGITS
    ract
    0.06
    .cid
    0.06
    dfs
    0.06
    固定
    0.06
     odp
    0.06
     desperately
    0.06
     Account
    0.06
     celebrates
    0.06
    ('|
    0.06
     Bers
    0.05
    Act Density 0.090%

    No Known Activations