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

    Neuronpedia

    INDEX
    Explanations

    key figures in philosophy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unspoken
    0.50
     academy
    0.44
    在这
    0.43
     aujourd
    0.43
     introduction
    0.43
    在那里
    0.42
     ba
    0.42
    jor
    0.41
     dẫn
    0.40
     faculty
    0.40
    POSITIVE LOGITS
     বাঙালিদের
    0.48
     cellulose
    0.48
    ينات
    0.47
    fires
    0.44
     بهره
    0.44
     fringes
    0.44
     मिळते
    0.44
     Silica
    0.43
     bactéries
    0.43
     Beware
    0.43
    Act Density 0.004%

    No Known Activations