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

    Neuronpedia

    INDEX
    Explanations

    import python transformers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bool
    0.41
     शिंदे
    0.39
    logger
    0.38
     boolean
    0.37
    Bool
    0.37
    boolean
    0.37
     скло
    0.37
    defined
    0.36
     टेन
    0.36
    False
    0.36
    POSITIVE LOGITS
    ($(
    0.40
    osphate
    0.39
    ługa
    0.39
    =$(
    0.38
    ()
    0.37
    alco
    0.37
    𝓰
    0.37
    ,$
    0.37
    وة
    0.37
    !।
    0.37
    Act Density 0.003%

    No Known Activations