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

    Neuronpedia

    INDEX
    Explanations

    gravitational constant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    錚
    0.44
    ρες
    0.40
    ":[{"
    0.39
    Opacity
    0.39
    GridLayout
    0.38
    二维码
    0.38
     Pdf
    0.37
    ㈤
    0.37
    Bru
    0.37
    াইজ
    0.36
    POSITIVE LOGITS
     law
    0.45
    மன்ற
    0.45
     imitation
    0.42
     prerog
    0.42
     imitating
    0.41
     imit
    0.41
     psych
    0.39
     prensa
    0.39
     physics
    0.39
     lawyers
    0.39
    Act Density 0.001%

    No Known Activations