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

    Neuronpedia

    INDEX
    Explanations

    -under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FORCE
    -0.07
     사용
    -0.07
    орд
    -0.07
    _xml
    -0.07
     içi
    -0.07
     في
    -0.06
     configs
    -0.06
     fake
    -0.06
    ाथ
    -0.06
    挑
    -0.06
    POSITIVE LOGITS
    (alert
    0.06
    STEM
    0.06
     Mission
    0.06
    BUTTONDOWN
    0.06
    933
    0.05
    =Math
    0.05
     خ
    0.05
     สถาน
    0.05
    ta
    0.05
    wine
    0.05
    Act Density 0.001%

    No Known Activations