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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating quantity or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Abst
    0.33
     Develop
    0.32
     Use
    0.32
     Manage
    0.31
     Don
    0.31
     আপনি
    0.31
     Placing
    0.30
     Assist
    0.30
     Bif
    0.30
     Assess
    0.30
    POSITIVE LOGITS
    .
    0.44
    an
    0.39
    é
    0.37
     वर्षीय
    0.37
    esimo
    0.36
    이
    0.36
    ри
    0.34
    дин
    0.34
    합니다
    0.33
    ه
    0.33
    Act Density 0.303%

    No Known Activations