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

    Neuronpedia

    INDEX
    Explanations

    academic journals/reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Snyder
    -0.07
    STORE
    -0.07
     edge
    -0.07
     snow
    -0.07
     len
    -0.07
     צר
    -0.07
     outs
    -0.06
    并不
    -0.06
    村
    -0.06
     amer
    -0.06
    POSITIVE LOGITS
     disruption
    0.08
    可能发生
    0.07
     ALLOW
    0.07
    ⎇
    0.07
    ㎑
    0.07
     elimin
    0.07
     уров
    0.07
     yaklaş
    0.07
     ?>↵↵↵
    0.07
    がら
    0.07
    Act Density 0.011%

    No Known Activations