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

    Neuronpedia

    INDEX
    Explanations

    food descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lieblings
    0.86
     Samurai
    0.85
     Time
    0.82
     Zuckerberg
    0.80
     Zucker
    0.79
     Ukrainian
    0.79
     Foods
    0.77
     Yogurt
    0.77
     abhängig
    0.77
     ਇੱਕ
    0.77
    POSITIVE LOGITS
    ד
    0.69
    𝙉
    0.68
    crs
    0.64
     hems
    0.64
    ле
    0.63
     sureties
    0.60
     spheres
    0.59
    лах
    0.59
    Мы
    0.59
     plaques
    0.58
    Act Density 0.000%

    No Known Activations