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

    Neuronpedia

    INDEX
    Explanations

    explanation of concepts or relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     equations
    0.47
     hates
    0.45
     necessities
    0.41
    ապ
    0.40
     drivers
    0.40
    Ꮷ
    0.39
     confining
    0.39
     Pong
    0.37
    ℅
    0.37
     researches
    0.37
    POSITIVE LOGITS
    最佳
    0.41
     Schritt
    0.40
    PHIL
    0.40
     أثناء
    0.39
    uchar
    0.39
     étape
    0.38
     أفضل
    0.38
     mekanisme
    0.38
    Step
    0.38
    Bamboo
    0.38
    Act Density 0.000%

    No Known Activations