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

    Neuronpedia

    INDEX
    Explanations

    book

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $o
    -0.07
     sendo
    -0.07
    QtCore
    -0.07
     obsession
    -0.06
     مى
    -0.06
     '</
    -0.06
    เปอร
    -0.06
     '../../../
    -0.06
    首
    -0.06
     prob
    -0.06
    POSITIVE LOGITS
     Sheep
    0.07
    즘
    0.06
    attle
    0.06
    ЎыџN
    0.06
     тебе
    0.06
    .onStart
    0.06
     bump
    0.06
    -в
    0.06
    went
    0.06
     undermined
    0.06
    Act Density 0.028%

    No Known Activations