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

    Neuronpedia

    INDEX
    Explanations

    explainability of formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bunnies
    0.60
     torneo
    0.53
    0.52
     choroby
    0.50
     níveis
    0.49
     aniversário
    0.49
     nhắn
    0.48
    رین
    0.48
     livelli
    0.48
    อนไลน์
    0.47
    POSITIVE LOGITS
    FAILED
    0.53
    IN
    0.50
    al
    0.48
    td
    0.48
    kh
    0.47
     Database
    0.47
     FAO
    0.47
    V
    0.47
    data
    0.47
    Ab
    0.47
    Act Density 0.000%

    No Known Activations