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

    Neuronpedia

    INDEX
    Explanations

    People and relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hal
    -0.07
    =message
    -0.07
    {l
    -0.07
     ישנם
    -0.07
     Osaka
    -0.07
    回升
    -0.06
     Weird
    -0.06
     salsa
    -0.06
     dildo
    -0.06
    'r
    -0.06
    POSITIVE LOGITS
    	suite
    0.08
    يمي
    0.08
    委
    0.07
    encode
    0.07
    明代
    0.07
    -viol
    0.07
     초기
    0.07
    èles
    0.07
     lã
    0.07
    扶持
    0.07
    Act Density 0.147%

    No Known Activations