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

    Neuronpedia

    INDEX
    Explanations

    emphatic assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interesante
    0.57
     légèrement
    0.56
     importante
    0.54
     vikt
    0.53
     importantes
    0.51
     Slightly
    0.49
     fontos
    0.47
     importants
    0.47
     slightly
    0.47
     কিছুটা
    0.47
    POSITIVE LOGITS
    简直
    1.11
     absolutely
    1.02
     literally
    0.97
     absolutamente
    0.96
     truly
    0.96
     practically
    0.93
     rival
    0.91
     буквально
    0.91
     utterly
    0.91
     rivals
    0.88
    Act Density 0.092%

    No Known Activations