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

    Neuronpedia

    INDEX
    Explanations

    decreasing throughout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是没有
    0.48
    套餐
    0.47
    oze
    0.47
    ائے
    0.46
     价
    0.46
    卖家
    0.46
    另一个
    0.45
    ሽታ
    0.45
     recoup
    0.45
    othelioma
    0.45
    POSITIVE LOGITS
     VL
    0.41
    GR
    0.40
     Thermodynamics
    0.39
    低
    0.38
    プラ
    0.38
    Design
    0.38
     pseud
    0.38
     Coulomb
    0.38
     LA
    0.38
     randomized
    0.37
    Act Density 0.000%

    No Known Activations