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

    Neuronpedia

    INDEX
    Explanations

    knows how to proceed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myself
    0.49
     yourself
    0.48
     oneself
    0.42
     jezelf
    0.42
     নিজেকে
    0.41
     Pleasure
    0.41
     Myself
    0.41
     merupakan
    0.41
     dient
    0.40
     তিনি
    0.39
    POSITIVE LOGITS
     recognizes
    0.52
     recognize
    0.47
     recognizing
    0.43
    认可
    0.43
     detects
    0.42
     recognises
    0.41
    Recogn
    0.40
    recogn
    0.39
     recognise
    0.39
     deem
    0.39
    Act Density 0.186%

    No Known Activations