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

    Neuronpedia

    INDEX
    Explanations

    files starting with a dot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ccccn
    0.42
     longitudine
    0.40
     cholest
    0.39
    ܡ
    0.39
    urlString
    0.39
    ♂
    0.38
    kinase
    0.38
    阉
    0.38
    earing
    0.37
     oldCount
    0.37
    POSITIVE LOGITS
     (.
    1.35
     `.
    1.31
    gitignore
    1.20
    /.
    1.13
     [.
    1.04
    (.
    1.02
    Dot
    1.02
    (".
    1.01
     Dot
    1.00
     .
    0.98
    Act Density 0.025%

    No Known Activations