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

    Neuronpedia

    INDEX
    Explanations

    single quote string delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arquivos
    0.47
     espagn
    0.45
     retreats
    0.44
     regressions
    0.43
     spirals
    0.40
     ইন্দো
    0.40
     carpeta
    0.39
     insertions
    0.38
     spheres
    0.38
     émer
    0.37
    POSITIVE LOGITS
     simplify
    0.43
     देऊ
    0.42
     modernize
    0.39
    Sci
    0.38
     Simplified
    0.38
     communicate
    0.38
     remind
    0.38
     speak
    0.38
    സ്ഥാന
    0.38
    的任务
    0.38
    Act Density 0.002%

    No Known Activations