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

    Neuronpedia

    INDEX
    Explanations

    different things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಸೆ
    0.46
    ប
    0.44
    谭
    0.40
    गतान
    0.38
     ஆர
    0.37
    ープ
    0.37
    الث
    0.36
    ㅂ
    0.36
    싹
    0.36
     தம்
    0.36
    POSITIVE LOGITS
     things
    2.30
     thing
    2.19
    Things
    2.08
    things
    2.03
     Things
    1.99
     THINGS
    1.82
     cosas
    1.81
     coisas
    1.78
    thing
    1.72
     вещей
    1.71
    Act Density 0.018%

    No Known Activations