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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     answered
    -0.07
    抗议
    -0.07
    scribed
    -0.07
    _USERNAME
    -0.07
    收敛
    -0.07
    奇异
    -0.07
    �
    -0.07
    啐
    -0.07
    转会
    -0.07
    .For
    -0.07
    POSITIVE LOGITS
     Leh
    0.08
    dong
    0.07
    (del
    0.07
     rund
    0.07
     FR
    0.06
    未经授权
    0.06
    :
↵
↵
    0.06
     track
    0.06
    olkata
    0.06
    -cache
    0.06
    Act Density 0.002%

    No Known Activations