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

    Neuronpedia

    INDEX
    Explanations

    Scientific research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mans
    -0.07
     '.'
    -0.07
    &_
    -0.06
     vztah
    -0.06
    }))
    -0.06
    _green
    -0.06
    931
    -0.06
    metal
    -0.06
    .api
    -0.06
    GetY
    -0.06
    POSITIVE LOGITS
     Kasım
    0.07
     suprem
    0.06
     исч
    0.06
     آسی
    0.06
     ArgumentException
    0.06
    -rec
    0.06
    eptal
    0.06
    जर
    0.06
     рей
    0.06
     fiss
    0.06
    Act Density 0.057%

    No Known Activations