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

    Neuronpedia

    INDEX
    Explanations

    training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ㄚ
    -0.07
    镡
    -0.06
    ripper
    -0.06
    Do
    -0.06
     PART
    -0.06
    个
    -0.06
    (Get
    -0.06
     chuck
    -0.06
    True
    -0.06
     opting
    -0.06
    POSITIVE LOGITS
     KH
    0.09
     Balk
    0.07
    的兴趣
    0.07
     psyched
    0.07
     Phillips
    0.07
    公交
    0.07
    筠
    0.07
     البلد
    0.07
    ="{{
    0.07
    _rectangle
    0.07
    Act Density 0.025%

    No Known Activations