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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     언어
    -0.07
    .Direction
    -0.06
    _RETURNTRANSFER
    -0.06
    _series
    -0.06
    .BO
    -0.06
     undis
    -0.06
     thước
    -0.06
    thumbnail
    -0.06
     adj
    -0.06
    .findIndex
    -0.06
    POSITIVE LOGITS
    ===============
    0.07
     impossible
    0.07
     crawled
    0.07
     enough
    0.06
     shall
    0.06
     ек
    0.06
     (>
    0.06
     assembler
    0.06
     Велик
    0.06
    %)
    0.06
    Act Density 0.002%

    No Known Activations