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

    Neuronpedia

    INDEX
    Explanations

    ever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    овых
    -0.07
    dır
    -0.07
    (resultSet
    -0.07
    運動
    -0.07
    histor
    -0.07
     различные
    -0.07
    كار
    -0.07
    ickým
    -0.06
    온
    -0.06
    _FT
    -0.06
    POSITIVE LOGITS
     smoke
    0.06
     FileOutputStream
    0.06
     regularization
    0.06
     Canonical
    0.06
     pork
    0.06
     cosmetic
    0.06
     SEND
    0.06
     supervised
    0.06
    ोश
    0.06
    otherwise
    0.06
    Act Density 0.013%

    No Known Activations