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

    Neuronpedia

    INDEX
    Explanations

    physical forces and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Msg
    0.99
    ln
    0.87
     choice
    0.87
    ेंग
    0.86
     çerçe
    0.85
    ErrorMessage
    0.83
    ৩
    0.81
    Mens
    0.81
    lt
    0.81
     semicolon
    0.80
    POSITIVE LOGITS
    गंज
    1.24
    ت
    1.22
    koliko
    1.21
    yani
    1.19
    yog
    1.15
     parli
    1.13
    㙋
    1.13
    ف
    1.12
     welches
    1.12
     cherche
    1.10
    Act Density 0.006%

    No Known Activations