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

    Neuronpedia

    INDEX
    Explanations

    programming and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mahm
    0.60
     Alford
    0.59
    }^{*}(\
    0.57
     Balfour
    0.56
     Clemens
    0.55
     Rong
    0.55
     Ahm
    0.54
     Manfred
    0.54
     Latham
    0.53
    ('*
    0.53
    POSITIVE LOGITS
     की
    0.43
     समझाने
    0.43
     শূন্য
    0.43
    grams
    0.42
     तोड़ने
    0.42
     labeling
    0.41
     紹介
    0.41
    ды
    0.41
     speakers
    0.40
     तीनों
    0.40
    Act Density 0.000%

    No Known Activations