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

    Neuronpedia

    INDEX
    Explanations

    svg code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     দায়
    0.44
    اکي
    0.43
    你去
    0.42
    اك
    0.42
    لبوم
    0.41
     diamètre
    0.40
     conhece
    0.40
     loser
    0.39
    اض
    0.38
     Fernseh
    0.38
    POSITIVE LOGITS
    itive
    0.46
    isive
    0.46
     interpolated
    0.44
    missive
    0.43
    ventus
    0.43
    intended
    0.42
    itate
    0.42
     भागों
    0.42
    inflammatory
    0.42
     Promises
    0.42
    Act Density 0.001%

    No Known Activations