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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оги
    -0.08
    =W
    -0.06
     surfing
    -0.06
    neapolis
    -0.06
    /j
    -0.06
    /P
    -0.06
    _templates
    -0.06
    醒
    -0.06
    'I
    -0.06
    olate
    -0.06
    POSITIVE LOGITS
    delegate
    0.07
    ины
    0.06
     outage
    0.06
     hdr
    0.06
     markup
    0.06
     gulp
    0.06
     vine
    0.06
     없어
    0.06
     keyCode
    0.06
     структу
    0.06
    Act Density 0.000%

    No Known Activations