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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    (alert
    -0.07
    葎
    -0.07
    裉
    -0.07
    gré
    -0.07
     Пере
    -0.07
    ."),↵
    -0.07
    𫰛
    -0.07
    破碎
    -0.07
     Greenland
    -0.07
    POSITIVE LOGITS
     pathetic
    0.08
    Sibling
    0.08
    AAA
    0.07
    たら
    0.07
    _Framework
    0.07
     irritating
    0.07
    移动端
    0.07
     Rebecca
    0.06
     Victim
    0.06
    ❥
    0.06
    Act Density 0.000%

    No Known Activations