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

    Neuronpedia

    INDEX
    Explanations

    code, python, and system calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    к
    1.45
     grep
    1.41
     beher
    1.33
    年在
    1.30
     göz
    1.29
    হ্য
    1.28
     grün
    1.28
     hujan
    1.28
     gegevens
    1.28
     indi
    1.26
    POSITIVE LOGITS
    ت
    1.66
    manship
    1.61
    tedir
    1.60
    เอา
    1.56
    т
    1.54
    ificato
    1.49
    uose
    1.48
    ר
    1.44
     đảo
    1.43
    otika
    1.43
    Act Density 0.000%

    No Known Activations