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

    Neuronpedia

    INDEX
    Explanations

    immune

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sid
    -0.07
    웸
    -0.07
    辅
    -0.06
    ញ
    -0.06
    perimental
    -0.06
     Quý
    -0.06
    
    -0.06
    .Movie
    -0.06
     citas
    -0.06
    _so
    -0.06
    POSITIVE LOGITS
     IndexError
    0.08
    ORIA
    0.08
    _coef
    0.07
     Falls
    0.07
     Balance
    0.07
     kale
    0.07
    ولي
    0.07
    ↧
    0.07
     restrain
    0.07
     corrosion
    0.07
    Act Density 0.025%

    No Known Activations