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

    Neuronpedia

    INDEX
    Explanations

    art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    调剂
    -0.07
    ってしまいます
    -0.07
     failure
    -0.07
    审批
    -0.07
    ❞
    -0.07
    "/>
    -0.07
     attack
    -0.07
    enson
    -0.06
    个
    -0.06
     Turn
    -0.06
    POSITIVE LOGITS
    柊
    0.08
    trys
    0.07
    adastrar
    0.07
    奓
    0.07
     Luft
    0.07
    _iters
    0.07
     sayılı
    0.07
    XMLLoader
    0.06
    _air
    0.06
    ރ
    0.06
    Act Density 0.039%

    No Known Activations