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

    Neuronpedia

    INDEX
    Explanations

    specific programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     headspace
    0.48
     činn
    0.47
    inz
    0.47
    alone
    0.45
     reass
    0.43
     malonyl
    0.43
    वर्ल्ड
    0.42
     vision
    0.42
     resumption
    0.42
     litter
    0.42
    POSITIVE LOGITS
     Correlations
    0.48
     README
    0.47
     Colored
    0.46
     Error
    0.46
     Mostrar
    0.46
     Mermaid
    0.44
    는데
    0.44
     curioso
    0.44
     Months
    0.43
    Colored
    0.43
    Act Density 0.002%

    No Known Activations