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

    Neuronpedia

    INDEX
    Explanations

    plot, politicians, Chávez

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یم
    0.62
    وع
    0.54
    O
    0.53
    یر
    0.50
    어를
    0.49
    중
    0.47
     המ
    0.47
     punctul
    0.46
    וד
    0.46
    ोटा
    0.45
    POSITIVE LOGITS
     politicians
    0.50
     бер
    0.47
     бере
    0.47
     аз
    0.46
    bl
    0.45
     calmness
    0.44
     auteurs
    0.44
     auteur
    0.44
     понима
    0.44
     berlang
    0.43
    Act Density 0.000%

    No Known Activations