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

    Neuronpedia

    INDEX
    Explanations

    interpersonal interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VERY
    -0.07
     stavu
    -0.06
     bald
    -0.06
    .Flag
    -0.06
     velké
    -0.06
    /*.
    -0.06
     elder
    -0.06
    =%.
    -0.06
     relativ
    -0.06
    (alias
    -0.06
    POSITIVE LOGITS
    annual
    0.07
     برنامه
    0.07
     ACM
    0.07
    ABC
    0.07
     dp
    0.07
     Continuous
    0.07
     statewide
    0.07
     pairwise
    0.07
     Melbourne
    0.07
    ड़क
    0.06
    Act Density 0.013%

    No Known Activations