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

    Neuronpedia

    INDEX
    Explanations

    listing abstract qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purest
    0.37
     kaisi
    0.36
     clearest
    0.35
     mãos
    0.35
    ौदा
    0.35
     municipales
    0.35
     ب
    0.34
     بأ
    0.34
    ufthansa
    0.34
    ाइव
    0.33
    POSITIVE LOGITS
    、
    1.40
    ፣
    1.14
    ,
    1.11
    ،
    1.09
    ၊
    1.09
     、
    1.00
    -,
    0.98
    ，
    0.92
     ,
    0.91
     ፣
    0.89
    Act Density 0.383%

    No Known Activations