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

    Neuronpedia

    INDEX
    Explanations

    or moral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     činn
    0.51
    nö
    0.50
     malonyl
    0.48
    inz
    0.48
     mencipt
    0.48
     whining
    0.48
     headspace
    0.47
     temperat
    0.47
    carn
    0.46
    怎样的
    0.46
    POSITIVE LOGITS
     Sorting
    0.52
     Rays
    0.50
     Correlations
    0.50
     README
    0.49
     Tumor
    0.48
     Upcoming
    0.48
     Links
    0.48
     Installation
    0.47
     Mostrar
    0.47
     Relationships
    0.46
    Act Density 0.000%

    No Known Activations