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

    Neuronpedia

    INDEX
    Explanations

    ium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ращи
    -0.07
     dicts
    -0.07
    く
    -0.06
     Gy
    -0.06
     intercepted
    -0.06
     bee
    -0.06
    SpecWarn
    -0.06
     obvykle
    -0.06
    [train
    -0.06
    かの
    -0.06
    POSITIVE LOGITS
     NAS
    0.07
     EntryPoint
    0.07
     فوق
    0.06
     <->
    0.06
     indemn
    0.06
     incompet
    0.06
     міста
    0.06
     اون
    0.06
     Fourier
    0.06
    .list
    0.06
    Act Density 0.003%

    No Known Activations