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

    Neuronpedia

    INDEX
    Explanations

    Specific entities after separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.43
    ，
    0.34
    .
    0.28
    、
    0.27
    "،
    0.26
    "",
    0.25
     ،
    0.24
    "],
    0.23
    0.23
    parsedBlock
    0.23
    POSITIVE LOGITS
    n
    0.29
    s
    0.27
     illetve
    0.25
    d
    0.25
     które
    0.25
    a
    0.24
     které
    0.23
    is
    0.23
    im
    0.22
    א
    0.22
    Act Density 0.412%

    No Known Activations