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

    Neuronpedia

    INDEX
    Explanations

    numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ELL
    -0.07
     unsettling
    -0.07
     情
    -0.07
    emer
    -0.06
    (Long
    -0.06
     ErrorMessage
    -0.06
    vals
    -0.06
    LogFile
    -0.06
    _go
    -0.06
    灵
    -0.06
    POSITIVE LOGITS
     серпня
    0.07
     Thông
    0.06
    .room
    0.06
     Como
    0.06
    물을
    0.06
    richText
    0.06
    .module
    0.06
     Zimbabwe
    0.06
    Como
    0.06
     روم
    0.06
    Act Density 0.008%

    No Known Activations