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

    Neuronpedia

    INDEX
    Explanations

    number lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ohnehin
    -0.08
     масштаб
    -0.08
     geh
    -0.07
     ся
    -0.07
    หนึ่ง
    -0.07
    schemas
    -0.07
     DCHECK
    -0.07
    äum
    -0.07
     unjust
    -0.07
    .Dom
    -0.07
    POSITIVE LOGITS
     भेल
    0.09
    Entries
    0.08
     mostly
    0.08
    Sorted
    0.08
    Grouped
    0.08
     []*
    0.08
    Duplicates
    0.08
     छन्
    0.08
    遗漏
    0.08
     miscellaneous
    0.08
    Act Density 0.094%

    No Known Activations