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

    Neuronpedia

    INDEX
    Explanations

    Vicuna creator or method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     megawatts
    0.43
     Midland
    0.42
    inhua
    0.42
     MJ
    0.42
     IF
    0.41
     मिताली
    0.40
     TD
    0.40
     ninja
    0.40
    BURTS
    0.40
     инг
    0.39
    POSITIVE LOGITS
    Vic
    0.54
     Vic
    0.52
     LMS
    0.49
     vic
    0.49
     Viceroy
    0.49
    Vict
    0.48
     Viktor
    0.47
    VIC
    0.45
     Ві
    0.44
    Vik
    0.42
    Act Density 0.013%

    No Known Activations