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

    Neuronpedia

    INDEX
    Explanations

    verb + ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ften
    0.46
    vet
    0.40
    YLE
    0.38
    പരമായ
    0.38
    ucceed
    0.38
    ewek
    0.37
    forder
    0.37
    UZ
    0.36
    AVE
    0.36
    ypass
    0.36
    POSITIVE LOGITS
    ing
    2.69
    ING
    2.39
    िंग
    2.36
    ings
    2.20
    િંગ
    2.08
    িং
    2.06
    ینگ
    1.77
    Ing
    1.70
    инг
    1.65
    INGS
    1.63
    Act Density 0.228%

    No Known Activations