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

    Neuronpedia

    INDEX
    Explanations

    social

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ampl
    -0.07
     ru
    -0.07
     lets
    -0.06
     Reyes
    -0.06
     multiplying
    -0.06
     Cure
    -0.06
     levy
    -0.06
    _mut
    -0.06
     lup
    -0.06
     peptide
    -0.06
    POSITIVE LOGITS
     social
    0.10
     Social
    0.09
    social
    0.07
     thảo
    0.07
    oS
    0.07
    Social
    0.07
     socialism
    0.07
    Trading
    0.07
     South
    0.07
     Apartments
    0.07
    Act Density 0.028%

    No Known Activations