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

    Neuronpedia

    INDEX
    Explanations

    master of skill or role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ми
    0.87
     воздуха
    0.77
    é
    0.76
    ф
    0.76
    ದ
    0.72
    ,
    0.71
     lumped
    0.69
    كل
    0.66
     tantrums
    0.66
     aired
    0.65
    POSITIVE LOGITS
     European
    0.75
     Monochrome
    0.75
     Pottery
    0.74
     Alemanha
    0.74
    (
    0.73
    </h2>
    0.72
    </u>
    0.71
     Tobacco
    0.71
     Caramel
    0.71
     Ceramic
    0.71
    Act Density 0.004%

    No Known Activations