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

    Neuronpedia

    INDEX
    Explanations

    separators or underlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大
    0.66
    غ
    0.63
    ف
    0.59
    ه
    0.58
    ফ
    0.57
    메
    0.57
    去
    0.56
    علم
    0.55
    数据
    0.54
    l
    0.54
    POSITIVE LOGITS
     eux
    0.47
     Wendy
    0.46
     viscoelastic
    0.46
     Shakespeare
    0.46
     canals
    0.46
    на
    0.45
     canal
    0.45
     Huo
    0.45
     राष्ट्रपति
    0.45
     Gérard
    0.45
    Act Density 0.002%

    No Known Activations