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

    Neuronpedia

    INDEX
    Explanations

    You

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    用人单位
    -0.08
    ipheral
    -0.07
     CHANNEL
    -0.07
    uten
    -0.07
    巨人
    -0.07
    쨩
    -0.07
    len
    -0.07
     NSMutable
    -0.06
    奖学金
    -0.06
    ords
    -0.06
    POSITIVE LOGITS
     newArr
    0.08
    idak
    0.08
    evento
    0.07
    对应
    0.07
     biking
    0.07
    cq
    0.07
    ダメ
    0.07
    心意
    0.07
     Wan
    0.07
     phải
    0.07
    Act Density 0.097%

    No Known Activations