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

    Neuronpedia

    INDEX
    Explanations

    requests for reasons why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bage
    0.37
    context
    0.35
     transduction
    0.35
     utiles
    0.34
    ಕ್
    0.34
     dhat
    0.34
     cache
    0.33
     equitable
    0.33
    شا
    0.33
     gratuitamente
    0.33
    POSITIVE LOGITS
     बताते
    0.44
     Cé
    0.44
     why
    0.42
     NOT
    0.40
    Це
    0.38
     SOME
    0.38
     热
    0.38
     Someone
    0.38
     To
    0.37
     这
    0.36
    Act Density 0.003%

    No Known Activations