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

    Neuronpedia

    INDEX
    Explanations

    variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    1.38
     ulter
    1.33
    р
    1.27
    at
    1.22
     effettu
    1.20
    ر
    1.18
    üle
    1.13
     toc
    1.13
     resulta
    1.12
     появления
    1.12
    POSITIVE LOGITS
    ग्विजय
    1.41
     modernize
    1.22
     Moż
    1.14
     आफ्टरनून
    1.12
     jeopardize
    1.10
     publicized
    1.09
     Бы
    1.09
    Eksterne
    1.07
    cą
    1.05
     Более
    1.05
    Act Density 0.247%

    No Known Activations