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

    Neuronpedia

    INDEX
    Explanations

    exam results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handlers
    -0.07
     Weiner
    -0.07
     Catal
    -0.07
     blocking
    -0.07
    aina
    -0.06
     Král
    -0.06
    免
    -0.06
    segments
    -0.06
    _tasks
    -0.06
     management
    -0.06
    POSITIVE LOGITS
     hiển
    0.07
    ngx
    0.06
     presented
    0.06
    Glyph
    0.06
    Locker
    0.06
     دانلود
    0.06
    วรร
    0.06
    んで
    0.06
     بیش
    0.05
     　　　　　　　　
    0.05
    Act Density 0.009%

    No Known Activations