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

    Neuronpedia

    INDEX
    Explanations

    reflection and becoming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hijab
    0.31
     telenov
    0.29
     soap
    0.26
     wipers
    0.26
     opts
    0.26
     unsatisfied
    0.26
     &#
    0.25
     Priyanka
    0.25
     coerced
    0.25
     zippers
    0.25
    POSITIVE LOGITS
    成為
    0.28
    become
    0.28
    Author
    0.27
    變成
    0.27
     Paperback
    0.27
    ற்
    0.26
    B
    0.26
     trở
    0.26
    becomes
    0.26
    iver
    0.26
    Act Density 0.000%

    No Known Activations