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
    func
    -0.07
    ülebilir
    -0.07
     Fox
    -0.07
    battle
    -0.07
    onia
    -0.07
    чний
    -0.07
    (Const
    -0.06
     Question
    -0.06
     besie
    -0.06
    recursive
    -0.06
    POSITIVE LOGITS
    องท
    0.06
    разд
    0.06
     Cran
    0.06
    0.06
    ImageRelation
    0.06
    .Channel
    0.06
     тиж
    0.06
     Αλ
    0.06
     asset
    0.06
    にも
    0.06
    Act Density 0.089%

    No Known Activations