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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PHOTO
    -0.08
    恧
    -0.07
     celle
    -0.07
     decline
    -0.07
    所以我
    -0.07
    teenth
    -0.07
    屆
    -0.07
    百余
    -0.07
    olk
    -0.07
     nw
    -0.07
    POSITIVE LOGITS
     Ramadan
    0.09
     Maintain
    0.08
    机械设备
    0.07
     Imam
    0.07
     behaving
    0.07
    ometers
    0.07
    _customer
    0.07
    _concat
    0.07
     DVDs
    0.07
    ဇ
    0.07
    Act Density 0.002%

    No Known Activations