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

    Neuronpedia

    INDEX
    Explanations

    words starting with S

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嚆
    0.46
    㡷
    0.45
    谜
    0.45
     pavil
    0.44
     百
    0.44
    題目
    0.44
    蜷
    0.43
    ༎
    0.41
    鐢
    0.41
    结论
    0.40
    POSITIVE LOGITS
     S
    0.87
     s
    0.61
    ociety
    0.60
    S
    0.58
     së
    0.56
     الس
    0.55
     slightly
    0.54
    ucceeded
    0.53
    ufficient
    0.52
     স
    0.52
    Act Density 0.078%

    No Known Activations