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
     labour
    -0.07
     Peygamber
    -0.07
     水
    -0.06
    unicode
    -0.06
    undred
    -0.06
     خواه
    -0.06
    -process
    -0.06
    _led
    -0.06
    (nd
    -0.06
     spyOn
    -0.06
    POSITIVE LOGITS
     affili
    0.07
    ैसल
    0.06
     mú
    0.06
    ظˆ
    0.06
    ACING
    0.06
    IRC
    0.06
    authorization
    0.06
    eview
    0.06
     genera
    0.05
    _COMPONENT
    0.05
    Act Density 0.034%

    No Known Activations