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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ந
    -0.09
     outcomes
    -0.08
     Outcomes
    -0.08
     değerlend
    -0.07
    өн
    -0.07
     vesel
    -0.07
     жилья
    -0.07
     હતા
    -0.07
    remarks
    -0.07
     πι
    -0.07
    POSITIVE LOGITS
     sinister
    0.08
    리스
    0.08
    qry
    0.08
     dragging
    0.08
     propagated
    0.08
     derivative
    0.07
     creeping
    0.07
    TOK
    0.07
     директор
    0.07
    _INCREMENT
    0.07
    Act Density 0.020%

    No Known Activations