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

    Neuronpedia

    INDEX
    Explanations

    riddles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entreg
    0.49
     directa
    0.49
     incongru
    0.49
    زيد
    0.49
     istot
    0.46
     ACTUAL
    0.46
     trapez
    0.45
     corrige
    0.45
     is
    0.44
    癢
    0.44
    POSITIVE LOGITS
    all
    0.50
    chemicals
    0.47
    oli
    0.47
    ua
    0.46
    ived
    0.46
    hr
    0.46
     Chemicals
    0.46
    il
    0.45
    ategory
    0.45
    orth
    0.45
    Act Density 0.016%

    No Known Activations