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

    Neuronpedia

    INDEX
    Explanations

    Autoimmune diseases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salient
    -0.09
     prag
    -0.08
    Experimental
    -0.08
     concom
    -0.08
    Temporal
    -0.07
     ancillary
    -0.07
     amel
    -0.07
    'ensemble
    -0.07
     Couture
    -0.07
     qualit
    -0.07
    POSITIVE LOGITS
     trillion
    0.09
     malfunction
    0.09
    亿
    0.08
    hurt
    0.08
     sped
    0.08
     billions
    0.08
     scared
    0.08
     váš
    0.08
     teen
    0.08
    人体
    0.08
    Act Density 0.251%

    No Known Activations