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

    Neuronpedia

    INDEX
    Explanations

    exclamation points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izin
    -0.07
    (Search
    -0.07
     Gratuit
    -0.07
    Disappear
    -0.07
     dist
    -0.07
     digest
    -0.06
    َم
    -0.06
    illos
    -0.06
     depressing
    -0.06
     gift
    -0.06
    POSITIVE LOGITS
     Crus
    0.14
     crus
    0.09
    her
    0.08
    forth
    0.08
    ovation
    0.06
     동안
    0.06
    CEF
    0.06
     sống
    0.06
    fortunately
    0.06
    .parsers
    0.06
    Act Density 0.002%

    No Known Activations