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

    Neuronpedia

    INDEX
    Explanations

    Str

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    責
    -0.07
    邪
    -0.06
     مشک
    -0.06
     engulf
    -0.06
    (||
    -0.06
     cljs
    -0.06
    _REMOTE
    -0.06
    national
    -0.06
     ｌ
    -0.06
     facilities
    -0.06
    POSITIVE LOGITS
     �
    0.07
    /conf
    0.07
    atti
    0.07
    ในช
    0.06
     博
    0.06
    dia
    0.06
     Cornell
    0.06
    Sym
    0.06
     Columbus
    0.06
     tonight
    0.06
    Act Density 0.000%

    No Known Activations