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

    Neuronpedia

    INDEX
    Explanations

    Research paper abstracts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     essentials
    -0.07
    HELL
    -0.07
    děl
    -0.06
     scales
    -0.06
     maintenance
    -0.06
     currentPage
    -0.06
     JavaScript
    -0.06
    _DEST
    -0.06
     cords
    -0.06
    /usr
    -0.06
    POSITIVE LOGITS
    $j
    0.07
     Ava
    0.07
    <unsigned
    0.06
    Reverse
    0.06
    언
    0.06
     özgür
    0.06
     jedis
    0.06
     erectile
    0.06
     '*
    0.06
     khuôn
    0.06
    Act Density 0.003%

    No Known Activations