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

    Neuronpedia

    INDEX
    Explanations

    how information is presented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.87
    ما
    0.77
    3
    0.77
    4
    0.72
    س
    0.72
    ip
    0.70
    ре
    0.67
    </b>
    0.67
    uc
    0.66
     and
    0.66
    POSITIVE LOGITS
    erent
    0.68
     различ
    0.68
    𝟘
    0.67
     पुरालेखित
    0.66
     pédicule
    0.65
     сами
    0.64
    ຊີ
    0.63
     déchets
    0.63
    ezi
    0.63
    यों
    0.62
    Act Density 0.000%

    No Known Activations