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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DY
    -0.07
    Early
    -0.07
     ít
    -0.07
    Yo
    -0.07
     xpath
    -0.06
    qml
    -0.06
    diğini
    -0.06
     Messages
    -0.06
    puty
    -0.06
     affecting
    -0.06
    POSITIVE LOGITS
     관리자
    0.07
    ifax
    0.06
     Mounted
    0.06
    ishing
    0.06
     tímto
    0.06
    )",
↵
    0.06
    contract
    0.06
     Kosten
    0.06
     slave
    0.06
     sonraki
    0.06
    Act Density 0.112%

    No Known Activations