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

    Neuronpedia

    INDEX
    Explanations

    ers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     авг
    -0.07
    遊
    -0.07
    蛇
    -0.06
    (docs
    -0.06
    REPORT
    -0.06
    游
    -0.06
     Knee
    -0.06
    ceiving
    -0.06
    最後
    -0.06
    .updateDynamic
    -0.06
    POSITIVE LOGITS
    Abort
    0.07
    Ale
    0.06
    	labels
    0.06
     glfw
    0.06
     punctuation
    0.06
    ybrid
    0.06
     Díky
    0.06
     Ale
    0.06
     alike
    0.06
     Tough
    0.06
    Act Density 0.000%

    No Known Activations