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

    Neuronpedia

    INDEX
    Explanations

    stretch and fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يز
    1.45
     skutecz
    1.34
    らは
    1.22
    يق
    1.18
     размера
    1.18
     размеров
    1.17
    шие
    1.16
    hade
    1.16
    τερα
    1.15
    يف
    1.13
    POSITIVE LOGITS
    ل
    1.50
    न
    1.21
    l
    1.09
    ל
    1.08
    Phir
    1.05
    ने
    0.99
    li
    0.97
    бо
    0.97
     euismod
    0.96
    }+
    0.95
    Act Density 0.003%

    No Known Activations