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

    Neuronpedia

    INDEX
    Explanations

    server operations and MIME types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    powered
    1.16
     सटे
    1.16
    一部
    1.12
    ある
    1.12
    вати
    1.11
    loat
    1.09
    𝗥
    1.05
    йня
    1.02
     counterpart
    1.02
    cks
    1.00
    POSITIVE LOGITS
    ר
    1.39
    ার
    1.23
     ejercer
    1.21
    ت
    1.14
     impregn
    1.12
     inverso
    1.10
     adamant
    1.10
     Indigo
    1.10
    ूहिक
    1.09
     grasa
    1.08
    Act Density 0.011%

    No Known Activations