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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ділу
    -0.07
     университ
    -0.06
    	T
    -0.06
     接
    -0.06
    hc
    -0.06
     furry
    -0.06
     xf
    -0.06
     Gas
    -0.06
     pa
    -0.06
    Dream
    -0.06
    POSITIVE LOGITS
     prematurely
    0.07
    ＼＼
    0.06
     laden
    0.06
     Decom
    0.06
    .bootstrapcdn
    0.06
     clin
    0.06
    INGER
    0.06
     cub
    0.06
    دمة
    0.06
     {}\
    0.06
    Act Density 0.000%

    No Known Activations