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

    Neuronpedia

    INDEX
    Explanations

    processes and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வரு
    0.22
     May
    0.21
     Maroc
    0.21
     zmieni
    0.21
     Britain
    0.21
     যায়
    0.21
     jackets
    0.21
     you
    0.20
     Calgary
    0.20
     juta
    0.20
    POSITIVE LOGITS
     באמצעות
    0.28
    ,
    0.27
    without
    0.26
     utilizzando
    0.25
     using
    0.25
     باستخدام
    0.25
    ת
    0.25
     utilizando
    0.25
     sesuai
    0.25
    א
    0.24
    Act Density 0.468%

    No Known Activations