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

    Neuronpedia

    INDEX
    Explanations

    number two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _chr
    -0.07
     شدند
    -0.06
     svých
    -0.06
     Yap
    -0.06
    avanaugh
    -0.06
     thế
    -0.06
    =>
    -0.06
    魚
    -0.06
     ammonia
    -0.06
     Profiles
    -0.06
    POSITIVE LOGITS
    mpl
    0.07
    хран
    0.07
     chased
    0.06
    .Extensions
    0.06
    ματα
    0.06
     tissue
    0.06
    \admin
    0.06
    glass
    0.06
    Eval
    0.06
    ा.
    0.06
    Act Density 0.012%

    No Known Activations