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

    Neuronpedia

    INDEX
    Explanations

    ability or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    และการ
    0.83
     การ
    0.82
    integrate
    0.78
     elevate
    0.77
     descanso
    0.76
    impose
    0.76
    การ
    0.76
     auftreten
    0.76
     eğitim
    0.76
     integrate
    0.75
    POSITIVE LOGITS
     exporter
    0.63
    Formatter
    0.53
     aff
    0.52
    ocoder
    0.52
     compiler
    0.51
    Clr
    0.51
     coder
    0.51
     commentator
    0.51
     router
    0.51
    Coder
    0.50
    Act Density 0.006%

    No Known Activations