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

    Neuronpedia

    INDEX
    Explanations

    foreign characters and word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utory
    0.46
    onicus
    0.40
    ozygous
    0.40
    arynge
    0.39
    ichert
    0.39
    iched
    0.39
    chinen
    0.38
    عليه
    0.38
    chond
    0.38
    ignées
    0.37
    POSITIVE LOGITS
    ﺲ
    0.36
    ץ
    0.35
    ь
    0.35
    ς
    0.34
    ът
    0.34
    ן
    0.34
    ם
    0.34
    ും
    0.33
    ף
    0.33
    );
    0.32
    Act Density 0.177%

    No Known Activations