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

    Neuronpedia

    INDEX
    Explanations

    ASCII art descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꭾ
    0.32
    بر
    0.30
    偌
    0.29
     Creo
    0.29
    ิตย์
    0.29
     इसको
    0.28
     Duchess
    0.28
    Concurrent
    0.28
     hunk
    0.28
     Balkan
    0.28
    POSITIVE LOGITS
    ik
    0.40
    é
    0.38
    o
    0.38
    im
    0.38
    and
    0.37
    oc
    0.37
     growths
    0.36
    ic
    0.36
    ide
    0.35
    op
    0.35
    Act Density 0.002%

    No Known Activations