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

    Neuronpedia

    INDEX
    Explanations

    weight loss and gain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وس
    0.69
    that
    0.67
    V
    0.63
     چاپ
    0.60
    this
    0.59
    isc
    0.57
    秒
    0.57
    ров
    0.57
    س
    0.56
    ispens
    0.56
    POSITIVE LOGITS
     dieting
    1.05
     obesity
    0.98
    减肥
    0.95
     Obesity
    0.93
     Keto
    0.90
     dieta
    0.84
     endomet
    0.83
     slimming
    0.79
    ダイエット
    0.79
     obesidad
    0.78
    Act Density 0.110%

    No Known Activations