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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liber
    -0.06
     ds
    -0.06
     fotbal
    -0.06
    aiser
    -0.06
    евой
    -0.06
    profile
    -0.06
    ери
    -0.06
     Uph
    -0.06
    Summary
    -0.06
    _nv
    -0.06
    POSITIVE LOGITS
     showdown
    0.08
     distinction
    0.07
    (clone
    0.07
     institute
    0.06
    .paginator
    0.06
     PropTypes
    0.06
    sidebar
    0.06
    tribution
    0.06
    	dataType
    0.06
    	pos
    0.06
    Act Density 0.042%

    No Known Activations