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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    打进
    -0.07
    intptr
    -0.07
     frac
    -0.06
     hade
    -0.06
    排毒
    -0.06
     ELF
    -0.06
    .large
    -0.06
    -turned
    -0.06
    벋
    -0.06
     bezpośredni
    -0.06
    POSITIVE LOGITS
    поз
    0.07
     reasonable
    0.07
     ')
↵
    0.07
    аниз
    0.07
    ibBundleOrNil
    0.07
    options
    0.07
    _options
    0.07
    ﺮ
    0.07
     journals
    0.07
     Kop
    0.07
    Act Density 0.012%

    No Known Activations