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

    Neuronpedia

    INDEX
    Explanations

    expression levels changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FDA
    -0.06
     nhất
    -0.06
     іншими
    -0.06
    _scale
    -0.06
    cích
    -0.06
    hil
    -0.06
    seudo
    -0.06
    しの
    -0.06
    _sn
    -0.06
     nons
    -0.06
    POSITIVE LOGITS
     Logger
    0.07
    评价
    0.07
     Gallagher
    0.06
     спад
    0.06
     �
    0.06
     QAction
    0.06
     Opt
    0.06
     Priest
    0.06
    _RESPONSE
    0.06
     Лит
    0.06
    Act Density 0.112%

    No Known Activations