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

    Neuronpedia

    INDEX
    Explanations

    verbs ending in ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     budding
    1.62
    સ
    1.48
    s
    1.46
    sylvania
    1.44
     searing
    1.41
    hereafter
    1.40
     simmering
    1.40
    데
    1.36
    স
    1.35
    Reactor
    1.35
    POSITIVE LOGITS
    هم
    1.83
    ли
    1.72
    redients
    1.57
     jen
    1.55
    त
    1.54
    шее
    1.50
    ्ज
    1.49
    ly
    1.48
    redient
    1.43
     وم
    1.42
    Act Density 1.540%

    No Known Activations