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

    Neuronpedia

    INDEX
    Explanations

    help hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Trevor
    0.41
    Dare
    0.38
    lovepoetry
    0.37
    beck
    0.37
    اونلو
    0.36
    প্তি
    0.36
     Nghị
    0.36
     Dare
    0.36
     Lynne
    0.36
     dared
    0.35
    POSITIVE LOGITS
     whe
    0.37
    semble
    0.37
    Mars
    0.36
     Mars
    0.36
    TOO
    0.35
     toa
    0.35
     eight
    0.34
     forty
    0.34
    ৪২
    0.33
    ('../
    0.33
    Act Density 0.012%

    No Known Activations