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

    Neuronpedia

    INDEX
    Explanations

    html lang="en"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Arizona
    0.84
    დი
    0.80
    Arizona
    0.79
    Java
    0.78
     didReceive
    0.78
     círculo
    0.77
    τητα
    0.77
     Alabama
    0.75
    Natural
    0.75
     Java
    0.74
    POSITIVE LOGITS
    FloatTensor
    0.75
    fact
    0.74
     всем
    0.73
     činjen
    0.73
    என்
    0.72
     фак
    0.72
    elem
    0.72
    確實
    0.71
    含む
    0.71
     conformément
    0.71
    Act Density 0.000%

    No Known Activations