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

    Neuronpedia

    INDEX
    Explanations

    **specific phrases or clauses**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     můžete
    0.81
     swojej
    0.79
    íte
    0.77
    anel
    0.75
    ına
    0.75
     שני
    0.73
     gördüğünüz
    0.73
    ısını
    0.73
    了两
    0.72
     예술
    0.72
    POSITIVE LOGITS
    दार
    0.80
     Dropout
    0.71
     बेर
    0.68
    И
    0.67
     Equals
    0.66
    䖝
    0.66
    ेड
    0.66
    води
    0.64
    フィ
    0.64
     zh
    0.64
    Act Density 0.000%

    No Known Activations