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

    Neuronpedia

    INDEX
    Explanations

    mixture or complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FO
    0.43
    HO
    0.41
     ingredient
    0.39
     Ingredient
    0.39
    Component
    0.39
    Option
    0.37
     Fo
    0.37
     উপাদান
    0.37
    Ingredient
    0.37
    Id
    0.36
    POSITIVE LOGITS
     mixture
    0.46
     quello
    0.43
    ものである
    0.43
    เอก
    0.43
    mixture
    0.42
     ones
    0.42
     கொண்டது
    0.41
     mezcla
    0.41
    ものです
    0.40
     смеси
    0.39
    Act Density 0.015%

    No Known Activations