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

    Neuronpedia

    INDEX
    Explanations

    discussion degrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    א
    0.64
    ק
    0.64
    י
    0.63
    צ
    0.63
    および
    0.60
    אן
    0.60
    ้ง
    0.59
    ก
    0.59
    ığı
    0.58
    󠁳
    0.58
    POSITIVE LOGITS
    y
    0.68
    al
    0.56
    o
    0.55
    t
    0.52
    cout
    0.51
     borders
    0.51
     svart
    0.51
    pres
    0.50
    genes
    0.50
    travel
    0.50
    Act Density 0.002%

    No Known Activations