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

    Neuronpedia

    INDEX
    Explanations

    delicious food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ennia
    0.44
     truly
    0.38
     Teal
    0.34
     içinde
    0.34
    umbent
    0.34
    -\
    0.33
     Kit
    0.33
     Hamburger
    0.33
     hes
    0.33
     convincingly
    0.33
    POSITIVE LOGITS
    ীকরণ
    0.36
    лох
    0.34
     按
    0.32
     mica
    0.32
    ॅमिली
    0.32
    ках
    0.32
    хра
    0.32
    лаш
    0.32
     démar
    0.32
    cevam
    0.32
    Act Density 0.003%

    No Known Activations