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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +"/
    0.46
    ("@
    0.44
    ("./
    0.43
    ('"
    0.43
    ("\
    0.42
    ("//
    0.42
    ("/
    0.42
    ("/")
    0.42
    ("/",
    0.42
    MapView
    0.42
    POSITIVE LOGITS
     x
    0.83
     α
    0.76
     θ
    0.71
     х
    0.69
     φ
    0.69
     π
    0.69
     ξ
    0.68
     µ
    0.67
     ω
    0.65
     β
    0.65
    Act Density 0.497%

    No Known Activations