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

    Neuronpedia

    INDEX
    Explanations

    ask for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ză
    1.01
    pthread
    0.96
    cję
    0.94
    ясь
    0.93
    acres
    0.90
    رات
    0.89
    器的
    0.86
    %>%
    0.86
    indruck
    0.85
     మైసూరు
    0.85
    POSITIVE LOGITS
     questions
    1.91
     permission
    1.67
     Questions
    1.67
     rhet
    1.46
     question
    1.43
     probing
    1.39
     Permission
    1.39
     asking
    1.38
     Asking
    1.38
     thăm
    1.37
    Act Density 0.098%

    No Known Activations