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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Different
    -0.07
    etcode
    -0.07
    sets
    -0.06
    erson
    -0.06
    serialization
    -0.06
     Approach
    -0.06
     ceiling
    -0.06
    _subtype
    -0.06
    riages
    -0.06
    axis
    -0.06
    POSITIVE LOGITS
    (da
    0.07
    ющая
    0.06
     calendars
    0.06
     sene
    0.06
    所
    0.06
    .Cho
    0.06
    _family
    0.06
                              ↵
    0.06
     November
    0.06
     Force
    0.06
    Act Density 0.006%

    No Known Activations