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

    Neuronpedia

    INDEX
    Explanations

    German words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lbl
    1.11
    ر
    1.11
    gms
    1.08
    ল
    1.03
    )|\
    1.03
     presumption
    1.02
    Mississippi
    1.02
    esi
    0.97
    uhi
    0.97
     basename
    0.96
    POSITIVE LOGITS
     avanzada
    1.17
    旨在
    1.16
    زیز
    1.16
    บาล
    1.14
     edifício
    1.12
     gebied
    1.10
    е
    1.10
    金融
    1.10
    ător
    1.10
     ampia
    1.10
    Act Density 0.001%

    No Known Activations