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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?!
    -0.08
    elia
    -0.07
    (win
    -0.07
    rng
    -0.07
    も
    -0.07
    跑
    -0.07
    武
    -0.07
    DDD
    -0.07
    oints
    -0.07
     Curl
    -0.07
    POSITIVE LOGITS
     את
    0.07
    新しい
    0.07
    生育
    0.07
     הרב
    0.07
    .maxLength
    0.07
    快递
    0.06
    സ
    0.06
     מסוג
    0.06
    Thêm
    0.06
    ufacturer
    0.06
    Act Density 0.043%

    No Known Activations