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

    Neuronpedia

    INDEX
    Explanations

    names ending in ney or ley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ingly
    0.41
    たり
    0.39
    compromising
    0.39
    ﷲ
    0.39
    lessly
    0.39
     estaremos
    0.39
     کبھی
    0.38
    sour
    0.38
    ð
    0.38
     שם
    0.38
    POSITIVE LOGITS
     impe
    0.44
     problems
    0.43
     ചേർ
    0.39
    iggs
    0.39
    indeki
    0.39
     fossils
    0.38
     cyclists
    0.38
    orem
    0.37
     rumoured
    0.37
     offices
    0.36
    Act Density 0.002%

    No Known Activations