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

    Neuronpedia

    INDEX
    Explanations

    conversational manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     заря
    0.52
    tır
    0.48
    voř
    0.48
     शुर
    0.47
     вироб
    0.47
    جين
    0.46
     напа
    0.46
    塁
    0.46
     ອ
    0.46
     составляют
    0.46
    POSITIVE LOGITS
     context
    0.52
     role
    0.51
     vicinity
    0.50
     civilian
    0.49
     or
    0.49
    ח
    0.49
     Q
    0.48
     direction
    0.47
     perspectives
    0.46
     cluster
    0.46
    Act Density 0.002%

    No Known Activations