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

    Neuronpedia

    INDEX
    Explanations

    historically, stress, european

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ngunit
    0.53
     Bagaimana
    0.49
    ным
    0.48
     samym
    0.46
     kelamin
    0.44
     sondern
    0.44
    錒
    0.44
     गोले
    0.44
    ைகளுக்கு
    0.42
     Ah
    0.42
    POSITIVE LOGITS
    ré
    0.47
    ysis
    0.44
    idu
    0.43
    iao
    0.42
    ependence
    0.42
    ónicas
    0.42
    oding
    0.41
    </td>
    0.41
    </body>
    0.40
    urope
    0.40
    Act Density 0.003%

    No Known Activations