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

    Neuronpedia

    INDEX
    Explanations

    guides and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immensely
    0.42
     Collin
    0.41
    ogenesis
    0.41
     industries
    0.41
    amicin
    0.41
     purest
    0.40
     Increasing
    0.39
     Sunlight
    0.39
     zooming
    0.39
     endeavor
    0.39
    POSITIVE LOGITS
     информации
    0.51
    Guides
    0.49
     informacji
    0.48
     рассказал
    0.48
     danych
    0.47
     hakkında
    0.46
     ngunit
    0.45
     сообщил
    0.44
     podataka
    0.44
    XR
    0.44
    Act Density 0.005%

    No Known Activations