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

    Neuronpedia

    INDEX
    Explanations

    ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nytt
    0.49
     producto
    0.49
    نات
    0.49
     produto
    0.48
     arquitect
    0.48
     función
    0.48
    是
    0.47
     fuentes
    0.45
     funktion
    0.45
     prij
    0.45
    POSITIVE LOGITS
    volving
    0.44
     entrenched
    0.42
    ו
    0.42
     असलेला
    0.42
    herent
    0.41
    abhavena
    0.41
    pot
    0.41
    ad
    0.39
    ებლ
    0.39
     Loth
    0.39
    Act Density 0.003%

    No Known Activations