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

    Neuronpedia

    INDEX
    Explanations

    categories and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енню
    -0.07
     بیم
    -0.06
    �
    -0.06
    以来
    -0.06
    古
    -0.06
    ढ़
    -0.06
    acciones
    -0.06
    ”?
    -0.06
     philippines
    -0.06
     výro
    -0.06
    POSITIVE LOGITS
    (bounds
    0.07
     Presenter
    0.07
    _axes
    0.07
    iode
    0.06
    Vtbl
    0.06
     CommandType
    0.06
    admin
    0.06
     Hassan
    0.06
     '',
↵
    0.06
    (',
    0.06
    Act Density 0.005%

    No Known Activations