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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    regelen
    0.62
     mica
    0.60
    Mockito
    0.59
    4
    0.57
     xiv
    0.56
    ๔
    0.56
     الشيطان
    0.55
     پورا
    0.55
     lays
    0.55
     tangible
    0.55
    POSITIVE LOGITS
    죵
    0.65
    പറ
    0.64
     custos
    0.62
     Souza
    0.61
    Crist
    0.59
     Cooperation
    0.58
     etkin
    0.57
     сосу
    0.57
     topl
    0.57
    там
    0.57
    Act Density 0.018%

    No Known Activations