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

    Neuronpedia

    INDEX
    Explanations

    Code/Writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Our
    -0.06
     haze
    -0.06
     yazılım
    -0.06
    'h
    -0.06
    Moon
    -0.06
     accounted
    -0.06
    ")==
    -0.06
    thalm
    -0.06
     graz
    -0.06
     khuẩn
    -0.06
    POSITIVE LOGITS
     diagnostic
    0.08
    E
    0.07
     général
    0.07
    权限
    0.07
     Ceiling
    0.07
     Animation
    0.07
     serbest
    0.07
     Ecc
    0.07
    /use
    0.07
     hassle
    0.06
    Act Density 0.000%

    No Known Activations