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

    Neuronpedia

    INDEX
    Explanations

    ComBat algorithm rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ODDS
    0.38
    Bra
    0.37
    ث
    0.37
    מבר
    0.36
     Бра
    0.35
     brochures
    0.35
    ссу
    0.35
    డ
    0.35
    θεί
    0.34
     fiz
    0.34
    POSITIVE LOGITS
    学家
    0.39
    etera
    0.39
    ective
    0.39
     Muhammadu
    0.38
    MaskInto
    0.38
    第五
    0.38
    第二
    0.37
    ANT
    0.37
    SPE
    0.37
    DbContext
    0.37
    Act Density 0.000%

    No Known Activations