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

    Neuronpedia

    INDEX
    Explanations

    express.use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    शेष
    1.07
    ᱚ
    1.06
    其他
    1.05
    плу
    1.05
    云南
    1.05
    绁
    1.05
    دید
    1.03
    高手
    1.03
    ␶
    1.03
    selves
    1.02
    POSITIVE LOGITS
     Bork
    1.15
    ร
    1.13
     reconocida
    1.09
     bądź
    1.09
    1.09
     hiç
    1.08
     impresionante
    1.08
     incrível
    1.08
     Fleming
    1.07
     incomparable
    1.06
    Act Density 0.002%

    No Known Activations