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

    Neuronpedia

    INDEX
    Explanations

    efficient code implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ைகோ
    0.47
    am
    0.46
    in
    0.45
    if
    0.43
    ps
    0.43
    In
    0.41
    흐
    0.40
    inch
    0.40
    kr
    0.40
     stabilizers
    0.40
    POSITIVE LOGITS
     প্রথমে
    0.47
     potentiel
    0.46
     Dinner
    0.44
     Bailly
    0.44
     Bugünkü
    0.44
     thence
    0.44
     വ്യത്യ
    0.43
    ăzi
    0.43
     Firenze
    0.43
     choroby
    0.43
    Act Density 0.003%

    No Known Activations