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

    Neuronpedia

    INDEX
    Explanations

    Ramadan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     joy
    -0.07
     Nh
    -0.07
    .init
    -0.07
    性
    -0.06
     커
    -0.06
     delighted
    -0.06
     Agility
    -0.06
    _attributes
    -0.06
    谢
    -0.06
     written
    -0.06
    POSITIVE LOGITS
    @register
    0.07
    too
    0.06
    atel
    0.06
    ustria
    0.06
     edilen
    0.06
    平台
    0.06
    픈
    0.06
     Butler
    0.06
     üzerinde
    0.06
    вою
    0.06
    Act Density 0.004%

    No Known Activations