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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guido
    -0.08
    Replacing
    -0.08
     corporal
    -0.08
    चक
    -0.07
    Kb
    -0.07
     مف
    -0.07
    -conf
    -0.07
     felt
    -0.07
     verkl
    -0.07
    _the
    -0.07
    POSITIVE LOGITS
     keywords
    0.09
    flush
    0.09
     Keywords
    0.08
    keywords
    0.08
     hashtags
    0.08
     Flush
    0.08
    Flush
    0.08
    keyword
    0.08
     Flair
    0.08
     cumplimiento
    0.08
    Act Density 0.006%

    No Known Activations