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

    Neuronpedia

    INDEX
    Explanations

    Filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    调
    -0.06
    (sigma
    -0.06
    roman
    -0.06
    _logout
    -0.06
    iband
    -0.06
    (Search
    -0.06
    fst
    -0.06
     pcs
    -0.06
    �
    -0.06
    apo
    -0.06
    POSITIVE LOGITS
     useRef
    0.07
    IC
    0.07
     narrative
    0.06
     ملی
    0.06
     Dataset
    0.06
    ,const
    0.06
     phường
    0.06
    itecture
    0.06
    .firstName
    0.06
     COMM
    0.06
    Act Density 0.208%

    No Known Activations