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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    版
    -0.07
     youths
    -0.06
    输
    -0.06
     reproduction
    -0.06
     �
    -0.06
    [block
    -0.06
     begged
    -0.06
     �
    -0.06
     must
    -0.06
    Experts
    -0.06
    POSITIVE LOGITS
    거리
    0.07
    ş
    0.06
    ţ
    0.06
    菲
    0.06
    -shell
    0.06
     collider
    0.06
     дли
    0.06
    *\
    0.06
    ,res
    0.06
    acceptable
    0.06
    Act Density 0.018%

    No Known Activations