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

    Neuronpedia

    INDEX
    Explanations

    grid coordinates and modulo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    versammlung
    -0.09
     libido
    -0.08
     cosmos
    -0.08
     Tip
    -0.08
    lene
    -0.08
     testosterone
    -0.07
     zost
    -0.07
     drinking
    -0.07
     रिलीज
    -0.07
     mouths
    -0.07
    POSITIVE LOGITS
    	row
    0.10
    (row
    0.10
    県
    0.10
     moden
    0.09
    =row
    0.09
     row
    0.09
    	pos
    0.09
    ான்
    0.08
    _row
    0.08
     grids
    0.08
    Act Density 0.018%

    No Known Activations