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

    Neuronpedia

    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.05
    :";
    1.03
     leyes
    0.90
     .;
    0.86
    ");
    0.86
     originale
    0.84
    )->
    0.81
    :");
    0.81
     ;$
    0.80
     ==>
    0.80
    POSITIVE LOGITS
    …
    0.67
     leverages
    0.67
     COVID
    0.65
     주목
    0.64
    ardom
    0.64
    getting
    0.64
     sanity
    0.63
     tricky
    0.63
    бор
    0.62
     cardinality
    0.61
    Act Density 1.227%

    No Known Activations