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

    Neuronpedia

    INDEX
    Explanations

    legal/financial disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hry
    -0.07
     Clean
    -0.06
     также
    -0.06
     synonym
    -0.06
     Також
    -0.06
     orn
    -0.06
    .level
    -0.06
    чного
    -0.06
    -0.06
    ของ
    -0.06
    POSITIVE LOGITS
     は
    0.06
    ,proto
    0.06
    이크
    0.06
    =nil
    0.06
     personas
    0.06
     hbox
    0.06
     ikt
    0.06
    LB
    0.06
    рош
    0.06
    .setScale
    0.06
    Act Density 0.003%

    No Known Activations