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

    Neuronpedia

    INDEX
    Explanations

    say numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    冲
    -0.08
    換
    -0.08
     HTC
    -0.07
     عن
    -0.07
    一刻
    -0.07
    如何看待
    -0.07
    爱奇
    -0.07
     RUN
    -0.07
    按下
    -0.07
    煞
    -0.06
    POSITIVE LOGITS
    :start
    0.07
     sciences
    0.06
    眉头
    0.06
    Sending
    0.06
     располож
    0.06
     increases
    0.06
     Authorities
    0.06
    넑
    0.06
    beit
    0.06
     lodging
    0.06
    Act Density 0.001%

    No Known Activations