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

    Neuronpedia

    INDEX
    Explanations

    woodpecker / Gradient Boosting Regression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    〕
    0.71
     model
    0.61
     electrolysis
    0.61
     sea
    0.59
     ES
    0.59
     in
    0.58
     знаем
    0.57
    ES
    0.56
     runway
    0.56
     }$
    0.55
    POSITIVE LOGITS
    ו
    0.75
    و
    0.71
    ઓ
    0.71
    ^{+}(
    0.64
    施術
    0.61
     подклю
    0.57
    ומי
    0.56
     reembol
    0.54
    orest
    0.53
     vzt
    0.53
    Act Density 0.001%

    No Known Activations