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

    Neuronpedia

    INDEX
    Explanations

    character encoding attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Beverungen
    0.48
     conical
    0.45
    िवेशन
    0.42
    deposited
    0.40
     excav
    0.40
    ሖ
    0.39
    歯
    0.39
    ᒃ
    0.39
     JButton
    0.38
     peroxidation
    0.38
    POSITIVE LOGITS
    UTF
    1.13
    utf
    1.12
     UTF
    1.09
     utf
    0.95
    Utf
    0.79
    ascii
    0.64
     Latin
    0.62
     ASCII
    0.58
    iso
    0.57
    ASCII
    0.56
    Act Density 0.005%

    No Known Activations