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

    Neuronpedia

    INDEX
    Explanations

    transition to a state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eller
    0.28
     yoki
    0.27
     vagy
    0.27
     või
    0.24
     eftersom
    0.24
     janë
    0.23
     کاهش
    0.23
     zmniejs
    0.23
     veya
    0.22
     nebo
    0.22
    POSITIVE LOGITS
     an
    0.33
     THE
    0.31
     একটি
    0.30
    成为
    0.29
    an
    0.29
     a
    0.28
    成為
    0.27
    become
    0.27
     become
    0.27
     ஒரு
    0.26
    Act Density 0.266%

    No Known Activations