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

    Neuronpedia

    INDEX
    Explanations

    drug names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    理
    -0.07
    áž
    -0.07
    ewish
    -0.06
    ambda
    -0.06
    (**
    -0.06
     목
    -0.06
    URI
    -0.06
     стандарт
    -0.06
    Icon
    -0.06
     DIG
    -0.06
    POSITIVE LOGITS
    -Jul
    0.07
    صة
    0.06
    ildren
    0.06
     Γεν
    0.06
    μενη
    0.06
    �
    0.06
    _WARN
    0.06
     oldu
    0.06
     Commod
    0.06
     sluts
    0.06
    Act Density 0.046%

    No Known Activations