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

    Neuronpedia

    INDEX
    Explanations

    filename without extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aby
    0.38
    etan
    0.38
    gram
    0.37
     heavenly
    0.34
    imme
    0.34
    ünk
    0.34
    藿
    0.34
    همه
    0.34
    తా
    0.34
    कुछ
    0.34
    POSITIVE LOGITS
     cmake
    0.43
     Chimie
    0.43
     års
    0.43
     syslog
    0.41
     contemplate
    0.39
     '__
    0.38
     katalog
    0.38
     شائع
    0.38
     plufieurs
    0.38
     ])
    0.38
    Act Density 0.000%

    No Known Activations