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

    Neuronpedia

    INDEX
    Explanations

    ingredients and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.49
     doenças
    0.45
     são
    0.44
     будут
    0.42
     są
    0.41
     saludables
    0.41
     истори
    0.40
     serão
    0.40
     здійсню
    0.40
    ড়ান্ত
    0.39
    POSITIVE LOGITS
    X
    0.42
    F
    0.42
    DE
    0.39
    E
    0.39
    S
    0.38
    L
    0.38
    path
    0.36
    pass
    0.36
    P
    0.36
    sh
    0.35
    Act Density 0.191%

    No Known Activations