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

    Neuronpedia

    INDEX
    Explanations

    changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الجم
    0.46
    cela
    0.41
     વચ્
    0.39
    toNumber
    0.38
     regla
    0.36
    стера
    0.36
    izia
    0.36
     conci
    0.36
     tos
    0.36
    =$(
    0.36
    POSITIVE LOGITS
     CHANGES
    0.50
     Changes
    0.45
    Changes
    0.42
    changes
    0.41
    係る
    0.39
     Compression
    0.39
    पीड़न
    0.38
     изменения
    0.38
    Supp
    0.38
     문제를
    0.37
    Act Density 0.000%

    No Known Activations