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

    Neuronpedia

    INDEX
    Explanations

    words starting with Op

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ост
    0.42
     объек
    0.39
    う
    0.37
     смо
    0.37
     зобра
    0.37
     изобра
    0.36
    ICES
    0.36
     ulter
    0.36
     постро
    0.36
    Ссылки
    0.36
    POSITIVE LOGITS
     Op
    0.75
     OP
    0.67
    Op
    0.66
     op
    0.63
     Opal
    0.62
     Opp
    0.55
     ओपी
    0.54
    INION
    0.53
     OPD
    0.52
    Opp
    0.50
    Act Density 0.017%

    No Known Activations