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

    Neuronpedia

    INDEX
    Explanations

    words ending in y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াদেশিক
    0.46
    Ư
    0.44
     Mali
    0.42
    skraft
    0.42
    NATIONAL
    0.41
    ین
    0.40
    Routine
    0.40
    alloy
    0.40
    ाइवेट
    0.40
     shockingly
    0.39
    POSITIVE LOGITS
     goodness
    0.57
     eyed
    0.51
     haired
    0.50
     pants
    0.50
     dispositions
    0.49
    ء
    0.47
    不清
    0.45
    outube
    0.44
    գ
    0.44
     cheeks
    0.43
    Act Density 0.027%

    No Known Activations