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

    Neuronpedia

    INDEX
    Explanations

    Code/foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LOW
    -0.07
    sur
    -0.06
     �
    -0.06
     write
    -0.06
    ноп
    -0.06
    menin
    -0.06
     linguistic
    -0.06
     argue
    -0.06
    尽管
    -0.06
     race
    -0.06
    POSITIVE LOGITS
    }@
    0.07
     постоян
    0.07
    .dataGridViewTextBoxColumn
    0.06
     الجديد
    0.06
    _router
    0.06
    ORAGE
    0.06
    allax
    0.06
    ForResult
    0.06
    essoa
    0.06
    LogLevel
    0.06
    Act Density 0.012%

    No Known Activations