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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Written
    -0.09
    Edition
    -0.08
    trfs
    -0.08
    oop
    -0.08
    第四
    -0.08
     prepend
    -0.07
    每个月
    -0.07
    ie
    -0.07
     Edition
    -0.07
    Categories
    -0.07
    POSITIVE LOGITS
     Model
    0.10
     models
    0.08
     the
    0.08
    נפגע
    0.08
    _models
    0.07
    懋
    0.07
     modelName
    0.07
     Mär
    0.06
     model
    0.06
     QPixmap
    0.06
    Act Density 0.126%

    No Known Activations