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

    Neuronpedia

    INDEX
    Explanations

    ure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .message
    -0.07
     telefon
    -0.06
     toujours
    -0.06
     Computational
    -0.06
     backers
    -0.06
    .Expression
    -0.06
    summ
    -0.06
     toplam
    -0.06
    EEE
    -0.06
     قص
    -0.06
    POSITIVE LOGITS
     Satan
    0.07
     scrolls
    0.06
    (predicate
    0.06
    填
    0.06
     reak
    0.06
    _level
    0.06
    vpn
    0.06
     "^
    0.06
     Warren
    0.06
     Quran
    0.06
    Act Density 0.000%

    No Known Activations