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

    Neuronpedia

    INDEX
    Explanations

    names and pronunciations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁣
    0.20
     ‬
    0.19
     probably
    0.19
     …
    0.18
    0.18
    ;
    0.18
     MMM
    0.18
     Firstly
    0.18
    ⁣⁣
    0.18
     Federated
    0.18
    POSITIVE LOGITS
    ynı
    0.20
     enfermed
    0.20
    ô
    0.19
    irt
    0.19
    udarstven
    0.19
    ona
    0.18
    iy
    0.18
     évén
    0.18
     മേഖ
    0.18
    ê
    0.18
    Act Density 0.169%

    No Known Activations