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

    Neuronpedia

    INDEX
    Explanations

    arguments and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ameri
    0.38
     xaxis
    0.37
     itself
    0.36
     JMJD
    0.36
     american
    0.35
     amazon
    0.35
    JUNE
    0.35
     республи
    0.35
     JSTOR
    0.35
     its
    0.34
    POSITIVE LOGITS
    inputs
    0.43
     inputs
    0.38
    Inputs
    0.37
    krit
    0.36
    álni
    0.36
    props
    0.35
    params
    0.35
    input
    0.35
    Input
    0.35
     validate
    0.35
    Act Density 0.006%

    No Known Activations