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

    Neuronpedia

    INDEX
    Explanations

    list items or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그리고
    0.42
     sitten
    0.41
     perception
    0.38
     wreckage
    0.38
     sogenannten
    0.37
    hemian
    0.37
    そして
    0.36
    HHHH
    0.36
     psychopath
    0.36
    ⺆
    0.35
    POSITIVE LOGITS
    <ul>
    1.07
    ：
    0.85
    *:
    0.75
    :*
    0.75
    :
    0.71
    :-
    0.71
     incluye
    0.71
    ):
    0.69
    以下の
    0.68
    ：（
    0.68
    Act Density 1.273%

    No Known Activations