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

    Neuronpedia

    INDEX
    Explanations

    question about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Miscellaneous
    0.47
     prób
    0.42
     कृपा
    0.42
    滀
    0.40
     Pray
    0.40
     Krug
    0.40
    坚定
    0.40
    酶
    0.39
    瀉
    0.39
     Cute
    0.39
    POSITIVE LOGITS
    èdent
    0.45
    personalised
    0.40
    acquired
    0.40
    맟
    0.39
    🤺
    0.38
     programme
    0.38
     {{\
    0.38
     personalised
    0.38
    association
    0.37
    轉換
    0.37
    Act Density 0.000%

    No Known Activations