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

    Neuronpedia

    INDEX
    Explanations

    program instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vibes
    0.43
    推送
    0.42
    ٍ
    0.41
     vibe
    0.41
    ta
    0.41
    Anime
    0.40
    RenderTarget
    0.40
     pushed
    0.39
     aimé
    0.39
    mersive
    0.38
    POSITIVE LOGITS
     BENEF
    0.41
     গেরিলা
    0.40
     Benefit
    0.39
    
    0.37
     Entre
    0.36
     Arabs
    0.36
    INPUT
    0.36
     线
    0.36
     입력
    0.35
     meteor
    0.35
    Act Density 0.027%

    No Known Activations