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

    Neuronpedia

    INDEX
    Explanations

    introduces examples or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     محصولات
    0.36
     comenc
    0.34
     trademarks
    0.32
     browsers
    0.32
     våra
    0.31
     motors
    0.30
     possuem
    0.30
     produkter
    0.30
     americanos
    0.30
     afbeelding
    0.29
    POSITIVE LOGITS
     Therefore
    0.52
     Misalnya
    0.50
     Hence
    0.49
     Thus
    0.49
     Örneğin
    0.48
     Например
    0.48
    也就是说
    0.47
    比如說
    0.46
     Ведь
    0.46
     Namely
    0.46
    Act Density 0.282%

    No Known Activations