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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riages
    -0.08
    chi
    -0.07
    _production
    -0.06
     रक
    -0.06
    Destination
    -0.06
    —that
    -0.06
     automation
    -0.06
     frozen
    -0.06
    Good
    -0.06
     zijn
    -0.06
    POSITIVE LOGITS
    GetProcAddress
    0.07
    거리
    0.06
    /community
    0.06
     stanice
    0.06
    /background
    0.06
     karakter
    0.06
    ша
    0.06
     Cherry
    0.06
    DetailsService
    0.06
     Pause
    0.06
    Act Density 0.180%

    No Known Activations