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

    Neuronpedia

    INDEX
    Explanations

    diet, aesthetics, weight loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     సహ
    0.41
     verschil
    0.40
    obot
    0.40
    ahrenheit
    0.40
    έχ
    0.39
     miteinander
    0.39
    暐
    0.39
     rumus
    0.38
     चेहरे
    0.38
     Ahn
    0.38
    POSITIVE LOGITS
    s
    0.54
     on
    0.51
    GTA
    0.50
    ی
    0.50
    ک
    0.49
    ڳ
    0.46
     ஏ
    0.44
    ご
    0.44
    New
    0.44
    BRO
    0.44
    Act Density 0.001%

    No Known Activations