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

    Neuronpedia

    INDEX
    Explanations

    OS module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stormed
    0.43
    ([],
    0.43
    在前
    0.41
     competent
    0.41
     valleys
    0.40
    اده
    0.40
     off
    0.40
     distinguishers
    0.38
     stagn
    0.38
     restrain
    0.38
    POSITIVE LOGITS
     OS
    0.77
     Os
    0.72
    操作系统
    0.70
    os
    0.69
    OS
    0.68
     os
    0.67
    environ
    0.66
     Ос
    0.63
    Os
    0.61
     OSX
    0.59
    Act Density 0.164%

    No Known Activations