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

    Neuronpedia

    INDEX
    Explanations

    specific filter matches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    0.55
     Class
    0.44
    Class
    0.41
     Um
    0.41
    TE
    0.40
    Icon
    0.40
     listing
    0.39
    Te
    0.39
     icon
    0.38
    Enum
    0.38
    POSITIVE LOGITS
     matchList
    0.50
    溸
    0.46
    apadam
    0.43
     tám
    0.42
     ম্যাচের
    0.42
    కి
    0.41
    試合
    0.40
    idée
    0.40
     sostitu
    0.40
    τι
    0.40
    Act Density 0.000%

    No Known Activations