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

    Neuronpedia

    INDEX
    Explanations

    Java collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    1.19
    न
    1.14
    t
    1.12
    ה
    1.12
    nın
    1.03
    ن
    1.00
    n
    0.93
    natal
    0.90
    க
    0.89
    ๆ
    0.87
    POSITIVE LOGITS
    𝒌
    1.09
    𝚅
    1.05
     spoiling
    1.05
     Pape
    1.01
     Итак
    1.01
    𝑺
    1.01
     adherents
    1.00
     sacrificial
    0.99
    𝒅
    0.99
    Ⲧ
    0.99
    Act Density 0.001%

    No Known Activations