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

    Neuronpedia

    INDEX
    Explanations

    multilingual translation requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    K
    0.46
     legion
    0.46
     tapa
    0.46
     Lieberman
    0.45
    rame
    0.44
    ga
    0.43
     replica
    0.42
    lift
    0.42
     Meade
    0.42
     insignia
    0.42
    POSITIVE LOGITS
    quele
    0.56
    inud
    0.50
    可是
    0.49
    прави
    0.49
    च
    0.48
    ポット
    0.46
     тобто
    0.46
     penyebab
    0.46
    允許
    0.46
     সহিংসতার
    0.45
    Act Density 0.003%

    No Known Activations