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

    Neuronpedia

    INDEX
    Explanations

    code snippets, descriptions, and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ફરિયાદ
    0.41
     herein
    0.41
     імен
    0.41
    បង្
    0.40
     成分
    0.38
    辜
    0.38
     xúc
    0.38
     পথিক
    0.38
     herewith
    0.38
    বীন্দ্র
    0.37
    POSITIVE LOGITS
     Rivals
    0.43
    oit
    0.42
     Leonardo
    0.40
     lavori
    0.40
    ILLE
    0.40
    ٹنگ
    0.39
     toy
    0.39
     Fleur
    0.38
    ▉
    0.38
    oque
    0.38
    Act Density 0.000%

    No Known Activations