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

    Neuronpedia

    INDEX
    Explanations

    Code and random strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CB
    -0.07
    ज़
    -0.06
     aos
    -0.06
     Ґ
    -0.06
    *h
    -0.06
     ACM
    -0.06
    >H
    -0.06
    	Grid
    -0.06
    Sen
    -0.06
     warehouses
    -0.06
    POSITIVE LOGITS
     pll
    0.07
     overlay
    0.07
    Pos
    0.06
    to
    0.06
    .:
    0.06
     pe
    0.06
     peel
    0.06
     po
    0.06
     spont
    0.06
     probl
    0.06
    Act Density 2.305%

    No Known Activations