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

    Neuronpedia

    INDEX
    Explanations

    quite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     décor
    -0.08
     στους
    -0.07
     apprentices
    -0.06
    と
    -0.06
     saddened
    -0.06
     лише
    -0.06
    เฉพาะ
    -0.06
     спор
    -0.06
     ون
    -0.06
    .problem
    -0.06
    POSITIVE LOGITS
    .componentInstance
    0.07
    منت
    0.06
    GRAM
    0.06
    _REQUEST
    0.06
    (reverse
    0.06
     embarrassment
    0.06
    Linux
    0.06
    engine
    0.06
     Math
    0.06
     Exhaust
    0.06
    Act Density 0.015%

    No Known Activations