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

    Neuronpedia

    INDEX
    Explanations

    word or phrase followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quando
    0.48
    ﺭ
    0.46
    Р
    0.46
    color
    0.45
    function
    0.44
     gimana
    0.44
     kako
    0.43
     poate
    0.43
    }$,
    0.43
     trader
    0.42
    POSITIVE LOGITS
    ຂອງ
    0.43
     నీ
    0.43
     هیچ
    0.42
    ध्य
    0.41
     географи
    0.41
    щены
    0.40
    约束
    0.40
    莼
    0.39
    मूलन
    0.38
    至於
    0.38
    Act Density 0.002%

    No Known Activations