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

    Neuronpedia

    INDEX
    Explanations

    URLs and specific websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    денциа
    0.69
     сот
    0.67
     withheld
    0.67
     intimidated
    0.67
     parallelism
    0.67
    FilePath
    0.66
     cien
    0.65
     weight
    0.65
     fatigued
    0.64
     verlei
    0.63
    POSITIVE LOGITS
     Preferably
    0.85
     Ideally
    0.77
     sdl
    0.76
    ヾ
    0.71
     rectMode
    0.71
     వివర
    0.69
     střed
    0.68
     शुभार
    0.68
    Ideally
    0.68
    vano
    0.67
    Act Density 0.001%

    No Known Activations