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

    Neuronpedia

    INDEX
    Explanations

    generate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wallet
    -0.07
    DEN
    -0.07
     airplanes
    -0.07
     ▼
    -0.07
     entertaining
    -0.06
     手
    -0.06
    <y
    -0.06
     Č
    -0.06
    Vue
    -0.06
     jsi
    -0.06
    POSITIVE LOGITS
     Award
    0.06
    _Length
    0.06
     abduction
    0.06
    _OS
    0.06
     encontr
    0.06
     fut
    0.06
    :e
    0.06
     Gingrich
    0.06
    _chip
    0.05
    екар
    0.05
    Act Density 0.119%

    No Known Activations