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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    []
    0.73
    where
    0.71
    ...
    0.66
    Where
    0.66
     where
    0.66
    {}
    0.65
    element
    0.64
    View
    0.62
    view
    0.61
    kde
    0.60
    POSITIVE LOGITS
    ᆷ
    0.86
    arii
    0.84
    ++)//
    0.82
    を用
    0.82
     선보
    0.80
     पौधे
    0.80
     Nemat
    0.79
     ziek
    0.78
     Merr
    0.78
     solub
    0.77
    Act Density 0.188%

    No Known Activations