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

    Neuronpedia

    INDEX
    Explanations

    conservative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parole
    -0.07
    _bo
    -0.06
    _nan
    -0.06
    swers
    -0.06
    춘
    -0.06
     acquitted
    -0.06
     plut
    -0.06
     employers
    -0.06
     trăm
    -0.05
    플
    -0.05
    POSITIVE LOGITS
    _ENCODING
    0.07
    \grid
    0.07
    estination
    0.07
    ious
    0.06
    fontSize
    0.06
     fireEvent
    0.06
    etically
    0.06
    ically
    0.06
     galaxies
    0.06
    Module
    0.06
    Act Density 0.220%

    No Known Activations