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

    Neuronpedia

    INDEX
    Explanations

    ab akh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     choral
    0.48
     trauer
    0.48
     dedu
    0.46
    ্দ্র
    0.46
    िज्या
    0.46
     clara
    0.45
     televised
    0.45
     farewell
    0.45
     exiled
    0.45
     dragState
    0.44
    POSITIVE LOGITS
    ”
    0.50
    aning
    0.45
    يد
    0.44
    ció
    0.44
    "
    0.43
     tăng
    0.43
    났
    0.43
    粮
    0.43
     bý
    0.42
    stances
    0.42
    Act Density 0.003%

    No Known Activations