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

    Neuronpedia

    INDEX
    Explanations

    from humble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Salmon
    0.38
     ita
    0.38
    essages
    0.36
    #
    0.35
     Input
    0.35
     Control
    0.35
     Jesus
    0.35
    >/</
    0.34
     Pressed
    0.34
    angkan
    0.34
    POSITIVE LOGITS
    beitung
    0.44
     મોટી
    0.43
     circumstellar
    0.42
     මිල
    0.41
     $=\
    0.40
    密度
    0.39
    ="@
    0.39
    㻴
    0.38
     misfortune
    0.38
    စျေး
    0.38
    Act Density 0.002%

    No Known Activations