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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    modules
    -0.07
    Positive
    -0.07
    __:
    -0.07
     รอง
    -0.07
    FTP
    -0.06
    มอ
    -0.06
    LogFile
    -0.06
     Tibet
    -0.06
    銷
    -0.06
     conductor
    -0.06
    POSITIVE LOGITS
     eyes
    0.06
    interpret
    0.06
     Leipzig
    0.06
    (arr
    0.06
    pread
    0.06
    esehen
    0.06
    .gen
    0.06
    .book
    0.06
    .keyboard
    0.06
     regarded
    0.06
    Act Density 0.002%

    No Known Activations