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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LL
    -0.07
    	col
    -0.07
     Flower
    -0.06
     cres
    -0.06
    	yy
    -0.06
    ebo
    -0.06
    _hours
    -0.06
     blast
    -0.06
    mark
    -0.06
    liced
    -0.06
    POSITIVE LOGITS
     embodied
    0.07
    Bộ
    0.07
     Cognitive
    0.06
     cognitive
    0.06
     hailed
    0.06
     doctrine
    0.06
    Narrated
    0.06
    .Ribbon
    0.06
    _receive
    0.06
     Death
    0.06
    Act Density 0.000%

    No Known Activations