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

    Neuronpedia

    INDEX
    Explanations

    consciousness, accuracy, equal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iste
    0.45
     contributo
    0.43
    istan
    0.42
     hostilities
    0.41
    ill
    0.40
    ູ
    0.40
     انف
    0.39
     ಜೋ
    0.39
    np
    0.39
    reliance
    0.39
    POSITIVE LOGITS
     কেননা
    0.43
     strips
    0.41
     însă
    0.41
     However
    0.40
     however
    0.40
     denotes
    0.40
     gdyż
    0.40
     hermosa
    0.39
     Whenever
    0.39
     bosques
    0.39
    Act Density 0.020%

    No Known Activations