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

    Neuronpedia

    INDEX
    Explanations

    digress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Matrix
    -0.07
    rego
    -0.07
     आद
    -0.06
     спож
    -0.06
     Carter
    -0.06
    _Tab
    -0.06
     Bib
    -0.06
     manuals
    -0.06
     foll
    -0.06
     STAT
    -0.06
    POSITIVE LOGITS
    -ret
    0.07
    ,response
    0.07
    ền
    0.07
     cohesive
    0.07
     QtAws
    0.07
    wordpress
    0.06
    ेशन
    0.06
    alf
    0.06
    ψης
    0.06
     яким
    0.06
    Act Density 0.047%

    No Known Activations