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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tekrar
    -0.08
     مسائل
    -0.07
     splendid
    -0.07
    very
    -0.07
    тро
    -0.07
     panor
    -0.06
     Grove
    -0.06
    _Blue
    -0.06
    гає
    -0.06
    кот
    -0.06
    POSITIVE LOGITS
    akening
    0.07
    INTERNAL
    0.06
     satisfied
    0.06
     DD
    0.06
    .mozilla
    0.06
     Innovative
    0.06
     goddess
    0.06
     patented
    0.06
    appa
    0.06
     occupied
    0.06
    Act Density 0.051%

    No Known Activations