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

    Neuronpedia

    INDEX
    Explanations

    when other solutions fail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     хоче
    0.84
    happiness
    0.83
    towards
    0.79
    ′
    0.75
    ถ้า
    0.74
     стоимости
    0.72
     ตุลาคม
    0.71
    dependencies
    0.71
    ′,
    0.70
     Goh
    0.70
    POSITIVE LOGITS
     снима
    0.87
     pocos
    0.84
    urang
    0.78
     évidence
    0.78
    明确
    0.78
    бычно
    0.78
     남아
    0.77
     evid
    0.76
     guste
    0.76
     menos
    0.75
    Act Density 0.001%

    No Known Activations