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

    Neuronpedia

    INDEX
    Explanations

    C++ includes and header files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sheds
    0.81
     കഴ
    0.73
     PSF
    0.73
    広
    0.72
     assesses
    0.72
     assessing
    0.69
     குற்ற
    0.69
     shed
    0.67
    0.67
     लाइस
    0.65
    POSITIVE LOGITS
     h
    1.53
    h
    1.50
    hpp
    1.40
    cpp
    1.29
     cpp
    1.28
     CPP
    1.12
    header
    1.02
    H
    1.02
    ｈ
    1.02
    hh
    1.00
    Act Density 0.012%

    No Known Activations