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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    け
    -0.07
     Adolf
    -0.06
    阿
    -0.06
    _mock
    -0.06
     graduates
    -0.06
     aks
    -0.06
    療
    -0.06
    LANG
    -0.06
     فرز
    -0.06
     ei
    -0.06
    POSITIVE LOGITS
     outgoing
    0.07
    ئ
    0.07
     Ngày
    0.07
    Ngày
    0.06
     Slav
    0.06
     Bakanlığı
    0.06
    _startup
    0.06
    воз
    0.06
    ว
    0.06
    Absolutely
    0.06
    Act Density 0.235%

    No Known Activations