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

    Neuronpedia

    INDEX
    Explanations

    clockwork followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    มัน
    0.51
    蟶
    0.48
    梫
    0.48
    ItemStack
    0.47
    㐄
    0.47
     Dish
    0.46
     Van
    0.46
     Illusion
    0.45
    agamanam
    0.45
     Antibodies
    0.45
    POSITIVE LOGITS
    et
    0.58
    t
    0.51
    n
    0.48
    d
    0.47
    cl
    0.47
     правом
    0.47
    fect
    0.45
    dives
    0.44
     kammam
    0.43
     tarda
    0.43
    Act Density 0.000%

    No Known Activations