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

    Neuronpedia

    INDEX
    Explanations

    explains what and why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     일반적으로
    0.39
    ስቃሴ
    0.36
     gestalten
    0.36
    ximately
    0.35
     postulated
    0.35
     fillColorSpace
    0.35
     approximates
    0.35
     peripher
    0.35
     moieties
    0.34
     periodicals
    0.34
    POSITIVE LOGITS
     Why
    0.56
     why
    0.55
    why
    0.55
     How
    0.51
     Почему
    0.49
    Why
    0.49
    जानिए
    0.48
     how
    0.47
    为什么
    0.47
     Cómo
    0.47
    Act Density 0.030%

    No Known Activations