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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     título
    -0.08
    double
    -0.07
    Pale
    -0.06
    ろう
    -0.06
    лав
    -0.06
     servers
    -0.06
    |int
    -0.06
     Wars
    -0.06
     getData
    -0.06
     Dul
    -0.06
    POSITIVE LOGITS
    ‌گذ
    0.07
    ας
    0.06
     clinically
    0.06
     Orwell
    0.06
     experienced
    0.06
     economist
    0.06
     جدا
    0.06
     quarterly
    0.06
     SETTINGS
    0.06
    _atoms
    0.06
    Act Density 0.010%

    No Known Activations