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

    Neuronpedia

    INDEX
    Explanations

    Modified Android Distributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    قي
    0.52
    <0xA3>
    0.50
    medieval
    0.50
    تي
    0.48
    ച
    0.48
    غذ
    0.48
    മാ
    0.47
    ڑے
    0.47
    انوي
    0.47
    нача
    0.46
    POSITIVE LOGITS
    6
    0.55
    3
    0.51
    aging
    0.50
     Mod
    0.47
    rom
    0.46
    enting
    0.46
     의한
    0.45
    4
    0.44
     (
    0.44
     δρα
    0.43
    Act Density 0.000%

    No Known Activations