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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tribution
    -0.07
    袖
    -0.06
     申博
    -0.06
    اشین
    -0.06
    _FINISH
    -0.06
    _Path
    -0.06
    писок
    -0.06
    Histogram
    -0.06
    oenix
    -0.06
     randomNumber
    -0.06
    POSITIVE LOGITS
     overarching
    0.07
    ’d
    0.07
     Bộ
    0.07
     individual
    0.07
    because
    0.07
     overseas
    0.07
     anterior
    0.07
    Broad
    0.07
     arcane
    0.07
    orsi
    0.07
    Act Density 0.023%

    No Known Activations