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

    Neuronpedia

    INDEX
    Explanations

    V marked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ancies
    0.52
    ates
    0.51
    as
    0.48
    il
    0.48
    cik
    0.46
    usk
    0.46
    ata
    0.44
     linge
    0.43
    atino
    0.42
    asin
    0.42
    POSITIVE LOGITS
    תי
    0.55
     hairy
    0.53
    וב
    0.53
    כ
    0.52
    τι
    0.52
    נ
    0.52
    Золо
    0.51
    רי
    0.47
     करणे
    0.47
    地图
    0.46
    Act Density 0.000%

    No Known Activations