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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ći
    -0.07
     Taxes
    -0.07
    lin
    -0.06
    (Collection
    -0.06
     Uz
    -0.06
     Padres
    -0.06
     thereafter
    -0.06
    ┬
    -0.06
    ▍▍▍▍▍▍▍▍
    -0.06
    ”↵
    -0.06
    POSITIVE LOGITS
    phabet
    0.06
    [float
    0.06
    	Returns
    0.06
    apsulation
    0.06
     사무
    0.06
    filepath
    0.06
    _ADDR
    0.06
     범
    0.06
    engl
    0.06
     vim
    0.06
    Act Density 0.001%

    No Known Activations