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

    Neuronpedia

    INDEX
    Explanations

    most common, shareholders, state notices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     up
    0.46
     abstracts
    0.44
     alleviating
    0.43
     blushed
    0.43
     activism
    0.43
    カルシ
    0.42
    áme
    0.42
     causation
    0.42
    ients
    0.42
     shenanigans
    0.42
    POSITIVE LOGITS
    巉
    0.44
    un
    0.44
    وك
    0.43
    ي
    0.43
    u
    0.42
    ⼯
    0.42
     plante
    0.42
    вет
    0.39
    imt
    0.39
    i
    0.39
    Act Density 0.002%

    No Known Activations