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

    Neuronpedia

    INDEX
    Explanations

    programming concepts or classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     internationally
    0.45
     EEUU
    0.45
     lucrative
    0.44
     Huawei
    0.44
     Caucasian
    0.43
     Statutory
    0.42
     aastal
    0.42
     Francisco
    0.41
     sulfur
    0.41
     specialising
    0.41
    POSITIVE LOGITS
    respon
    0.48
    Confirm
    0.48
    Diam
    0.47
    Allen
    0.47
    Lo
    0.46
     או
    0.46
    êmes
    0.46
    Bra
    0.46
    Moder
    0.46
    Whi
    0.46
    Act Density 0.016%

    No Known Activations