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

    Neuronpedia

    INDEX
    Explanations

    adding code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    变化
    -0.07
     insurer
    -0.07
     conscience
    -0.07
    (Get
    -0.07
    _require
    -0.06
     wedding
    -0.06
     Lahore
    -0.06
    ケース
    -0.06
    μφωνα
    -0.06
    iani
    -0.06
    POSITIVE LOGITS
     učitel
    0.06
     yakın
    0.06
     effet
    0.06
    lü
    0.06
     integrates
    0.06
     있다
    0.06
    lı
    0.06
     introduces
    0.06
    [length
    0.06
    ogo
    0.06
    Act Density 0.008%

    No Known Activations