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

    Neuronpedia

    INDEX
    Explanations

    based on premise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    જી
    1.28
    Ther
    1.22
    ajara
    1.19
    eral
    1.18
     llevan
    1.14
    redirectTo
    1.14
    helper
    1.14
    шения
    1.12
     jerseys
    1.10
     querido
    1.10
    POSITIVE LOGITS
     اساس
    1.28
    basis
    1.26
     basis
    1.25
     основе
    1.25
    的基础
    1.23
    newdata
    1.17
    依据
    1.14
     fakta
    1.13
    参考に
    1.12
    THREAD
    1.11
    Act Density 0.281%

    No Known Activations