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

    Neuronpedia

    INDEX
    Explanations

    impacts, changes, or effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    通り
    -0.07
     정책
    -0.07
    _props
    -0.06
    prev
    -0.06
     minion
    -0.06
     drinks
    -0.06
    ross
    -0.06
     arterial
    -0.06
    端
    -0.06
     Parker
    -0.06
    POSITIVE LOGITS
     There
    0.06
     вам
    0.06
     THERE
    0.06
    texture
    0.06
    /vue
    0.06
     Jul
    0.06
     freshness
    0.06
     야
    0.06
    ؟
    0.06
     відкрит
    0.06
    Act Density 0.065%

    No Known Activations