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

    Neuronpedia

    INDEX
    Explanations

    Nordic, EDF, Gallifrey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ور
    1.07
    ’”
    0.90
    amme
    0.87
    itism
    0.87
    ită
    0.83
    מצע
    0.83
    onis
    0.82
    يں
    0.82
    &=&
    0.82
    ység
    0.82
    POSITIVE LOGITS
    .
    1.61
    ↵
    1.23
    t
    1.13
    на
    1.12
    т
    1.11
    ं
    1.06
    ።
    1.05
    ла
    1.04
     a
    1.02
    ני
    0.98
    Act Density 0.000%

    No Known Activations