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

    Neuronpedia

    INDEX
    Explanations

    questioning existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     قدر
    0.47
     reliance
    0.45
     E
    0.45
     quand
    0.43
     potenza
    0.42
    un
    0.42
     also
    0.42
     interactions
    0.41
     se
    0.41
     austerity
    0.40
    POSITIVE LOGITS
    akaranam
    0.55
    ించాడు
    0.52
    ാണ
    0.51
    हदी
    0.50
    ewnątrz
    0.50
     женой
    0.50
    兒子
    0.49
    शिंगटन
    0.49
    ပါ။
    0.48
     внутри
    0.48
    Act Density 0.001%

    No Known Activations