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
    _S
    -0.07
     removeFrom
    -0.06
    _ro
    -0.06
    .`
    -0.06
    …”
    -0.06
    __)↵
    -0.06
     rocked
    -0.06
    verbosity
    -0.06
     metros
    -0.06
    ательно
    -0.06
    POSITIVE LOGITS
     пояс
    0.07
     somehow
    0.07
     Islanders
    0.07
    (rows
    0.07
     ích
    0.06
    тов
    0.06
    -existing
    0.06
     dishes
    0.06
     ecc
    0.06
    узы
    0.06
    Act Density 0.017%

    No Known Activations