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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cougar
    -0.07
    .simpleButton
    -0.07
     recurrence
    -0.07
    PASSWORD
    -0.07
    categoryId
    -0.07
    _indicator
    -0.06
    龇
    -0.06
    😽
    -0.06
     Matthews
    -0.06
     deficits
    -0.06
    POSITIVE LOGITS
     lm
    0.08
    угл
    0.08
     syntax
    0.07
    妨
    0.07
     long
    0.07
    бр
    0.07
    ant
    0.07
    .want
    0.07
    أحدث
    0.07
     Where
    0.06
    Act Density 0.001%

    No Known Activations