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

    Neuronpedia

    INDEX
    Explanations

    _gr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pdf
    -0.07
    'M
    -0.06
     trở
    -0.06
    tı
    -0.06
    остей
    -0.06
    ’B
    -0.06
     Aerospace
    -0.06
    endid
    -0.06
     봐
    -0.06
    сю
    -0.06
    POSITIVE LOGITS
     heals
    0.07
     offsetof
    0.07
     Vice
    0.06
    JK
    0.06
    ATIC
    0.06
     substrate
    0.06
    lâm
    0.06
    traditional
    0.06
    Completion
    0.06
     umbrella
    0.06
    Act Density 0.001%

    No Known Activations