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

    Neuronpedia

    INDEX
    Explanations

    Time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     INDEX
    -0.06
    _after
    -0.06
     الكه
    -0.06
     comply
    -0.06
    77
    -0.06
     Walters
    -0.06
     flank
    -0.06
    EO
    -0.06
    Item
    -0.06
     Eve
    -0.06
    POSITIVE LOGITS
     opravdu
    0.08
     सद
    0.07
     konusu
    0.07
    _CAR
    0.06
     stalking
    0.06
     sluts
    0.06
    нями
    0.06
    .createNew
    0.06
    ább
    0.06
    .FILES
    0.06
    Act Density 0.057%

    No Known Activations