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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.81
     estekak
    -0.62
    FailureListener
    -0.61
    slidesToShow
    -0.60
     beginnetje
    -0.60
     незавершена
    -0.60
     المعيارى
    -0.59
     createSlice
    -0.59
    BagConstraints
    -0.58
    তথ্যসূত্র
    -0.58
    POSITIVE LOGITS
     declare
    0.52
     declared
    0.51
     mentioned
    0.50
     Travels
    0.49
     triumphantly
    0.47
    ỗi
    0.46
    არი
    0.46
    ecord
    0.45
     oath
    0.45
     credited
    0.45
    Act Density 0.009%

    No Known Activations