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

    Neuronpedia

    INDEX
    Explanations

    numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ډول
    0.17
     एखाद्या
    0.17
     appease
    0.17
     هم
    0.17
    cription
    0.17
     ٻ
    0.16
     في
    0.16
     اه
    0.16
     StringSet
    0.16
     sabotage
    0.16
    POSITIVE LOGITS
    0
    0.30
    -
    0.27
    8
    0.25
    ０
    0.25
     दिवसीय
    0.25
    5
    0.25
    р
    0.24
    он
    0.24
    4
    0.24
    %-
    0.23
    Act Density 0.717%

    No Known Activations