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

    Neuronpedia

    INDEX
    Explanations

    but introduces contrast or continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ılarak
    0.35
    ውነ
    0.32
    ço
    0.32
    ı
    0.31
     Reducing
    0.31
    verages
    0.29
    ğin
    0.29
     ignorant
    0.29
    iseksi
    0.29
    AW
    0.29
    POSITIVE LOGITS
     demás
    0.36
     respectivos
    0.33
     diversos
    0.30
     algod
    0.30
     vencer
    0.30
     beserta
    0.30
     lainnya
    0.29
     respectivas
    0.29
     войска
    0.29
     quaisquer
    0.29
    Act Density 0.000%

    No Known Activations