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

    Neuronpedia

    INDEX
    Explanations

    hearing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    svm
    -0.07
     Το
    -0.07
    スク
    -0.06
     κου
    -0.06
    َال
    -0.06
    �
    -0.06
     พ
    -0.06
    لاین
    -0.06
     Frontier
    -0.06
     الشم
    -0.06
    POSITIVE LOGITS
     Seahawks
    0.07
     reversible
    0.06
    .↵↵↵↵↵↵↵↵↵↵
    0.06
     Palest
    0.06
    ERCHANTABILITY
    0.06
    verbs
    0.06
    izin
    0.06
    Lint
    0.06
     Nodo
    0.06
    _TAG
    0.06
    Act Density 0.017%

    No Known Activations