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

    Neuronpedia

    INDEX
    Explanations

    analogies like baking cookies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ങ്ങളിലും
    0.47
     gratefully
    0.46
    imir
    0.46
     explor
    0.44
     fier
    0.44
     exposé
    0.44
    ewski
    0.43
     zudem
    0.42
    ventures
    0.41
    sean
    0.40
    POSITIVE LOGITS
     थे
    0.49
     хлоп
    0.47
    দ
    0.46
     группы
    0.46
     jobNumber
    0.44
     ছিল
    0.44
     cỡ
    0.44
     ছিলেন
    0.43
     бе
    0.43
     وخ
    0.43
    Act Density 0.005%

    No Known Activations