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

    Neuronpedia

    INDEX
    Explanations

    document, window, DOM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rund
    0.42
     wspom
    0.41
    人力
    0.41
     rundt
    0.40
    随后
    0.38
     schne
    0.38
    امام
    0.38
     rond
    0.38
    (*´
    0.38
    izuje
    0.37
    POSITIVE LOGITS
     Stomach
    0.44
    psilon
    0.41
     Aspir
    0.41
     Poll
    0.38
     Tanaka
    0.36
     Cus
    0.36
     Guardiola
    0.36
     stomach
    0.35
     Poison
    0.35
     Pharmac
    0.35
    Act Density 0.000%

    No Known Activations