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

    Neuronpedia

    INDEX
    Explanations

    Programming, Japanese mixed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    되지
    -0.07
    mites
    -0.07
     BODY
    -0.06
     sacked
    -0.06
     lessons
    -0.06
    ，还
    -0.06
    оба
    -0.06
     декабря
    -0.06
    /'↵
    -0.06
    ट
    -0.06
    POSITIVE LOGITS
    _MAC
    0.06
    <|eot_id|>
    0.06
     familiarity
    0.06
     Attr
    0.06
     gardens
    0.06
    Malloc
    0.06
     ま
    0.06
     xOffset
    0.06
    ENABLE
    0.06
    gcd
    0.06
    Act Density 0.149%

    No Known Activations