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

    Neuronpedia

    INDEX
    Explanations

    lists and options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	with
    -0.07
     Rajasthan
    -0.07
    染
    -0.07
    TODO
    -0.07
     Surrey
    -0.07
    Fear
    -0.07
    ]("
    -0.07
     Three
    -0.07
     welche
    -0.06
     Destruction
    -0.06
    POSITIVE LOGITS
    lyn
    0.07
    coni
    0.06
     cv
    0.06
     heirs
    0.06
     kl
    0.06
    _ped
    0.06
    _vi
    0.06
     gaping
    0.06
     respir
    0.05
    laz
    0.05
    Act Density 0.002%

    No Known Activations