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

    Neuronpedia

    INDEX
    Explanations

    account identification details

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    去哪里
    -0.08
    这笔
    -0.08
    ).*
    -0.07
    �
    -0.07
    吸引了
    -0.07
     Zucker
    -0.07
    .books
    -0.07
    辣
    -0.07
    basket
    -0.07
    .apiUrl
    -0.07
    POSITIVE LOGITS
    쇠
    0.07
    耶�
    0.07
     LOS
    0.06
     Fernando
    0.06
    〼
    0.06
    aterial
    0.06
     ó
    0.06
    _PROTO
    0.06
    炜
    0.06
    casting
    0.06
    Act Density 0.000%

    No Known Activations