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

    Neuronpedia

    INDEX
    Explanations

    configuration size, failing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alcoved
    0.54
     atthakath
    0.54
     удобно
    0.53
     konsumen
    0.53
     accommodating
    0.53
     understandably
    0.51
     вдоль
    0.51
    вите
    0.50
     Раз
    0.50
     Règlement
    0.50
    POSITIVE LOGITS
    t
    0.84
    y
    0.69
    n
    0.68
    l
    0.68
    o
    0.66
    i
    0.61
    it
    0.60
    r
    0.58
    en
    0.58
    ل
    0.57
    Act Density 0.000%

    No Known Activations