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

    Neuronpedia

    INDEX
    Explanations

    program code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FORE
    0.41
    Sprites
    0.39
     sprites
    0.38
    𝕤
    0.38
     আল
    0.38
    ドー
    0.37
     Chel
    0.37
     htmlFor
    0.36
     August
    0.35
     Tut
    0.35
    POSITIVE LOGITS
    listar
    0.47
    jian
    0.37
     pertains
    0.37
    ന്തപു
    0.36
    kontrol
    0.35
     conoscere
    0.34
    integrate
    0.34
    iran
    0.34
    ancienne
    0.34
    na
    0.34
    Act Density 0.088%

    No Known Activations