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

    Neuronpedia

    INDEX
    Explanations

    code blocks and programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    0.70
    ↵
    0.70
    ಕ
    0.70
    ování
    0.68
    istiwa
    0.66
    </sup>
    0.65
    R
    0.65
    ות
    0.64
    S
    0.63
    哃
    0.61
    POSITIVE LOGITS
     condos
    0.96
    reements
    0.89
    ᱩ
    0.84
     стекла
    0.82
    ကာ
    0.81
    orderLine
    0.81
     conditioners
    0.80
    MBOLS
    0.78
    গো
    0.78
     dealings
    0.77
    Act Density 0.003%

    No Known Activations