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

    Neuronpedia

    INDEX
    Explanations

    code module names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     världen
    0.45
    蠵
    0.40
    mien
    0.39
     معیار
    0.38
    ⓤ
    0.38
    meria
    0.38
     హె
    0.38
     ಹೇ
    0.38
    aniyati
    0.38
     Características
    0.37
    POSITIVE LOGITS
    ,
    0.64
    、
    0.53
    ،
    0.50
     पण
    0.49
    )
    0.47
    ,}
    0.47
    }
    0.46
    ]
    0.46
    ሦ
    0.45
     but
    0.45
    Act Density 0.002%

    No Known Activations