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

    Neuronpedia

    INDEX
    Explanations

    metabolic changes, health, benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.71
     kuten
    0.70
    ਰ
    0.68
    ر
    0.66
    at
    0.65
    ש
    0.64
     \,.
    0.61
     kuin
    0.60
    ul
    0.59
    িয়ে
    0.56
    POSITIVE LOGITS
    ார்
    0.81
    ー
    0.80
    춰
    0.77
    ní
    0.76
    好
    0.75
    أ
    0.75
    ᱘
    0.73
    It
    0.73
    ceğ
    0.73
    社会主义
    0.72
    Act Density 0.001%

    No Known Activations