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

    Neuronpedia

    INDEX
    Explanations

    language-specific punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    0.51
    tek
    0.50
    ts
    0.49
    se
    0.48
    poles
    0.48
    ο
    0.48
    politik
    0.47
    ский
    0.47
    sef
    0.47
    pi
    0.46
    POSITIVE LOGITS
    】，
    0.57
     كه
    0.57
    }};
    0.54
    }.}
    0.52
     khán
    0.52
     نجي
    0.52
     zegt
    0.51
    حي
    0.50
     reduz
    0.50
     Vorstand
    0.50
    Act Density 0.000%

    No Known Activations