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

    Neuronpedia

    INDEX
    Explanations

    explanation of communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chamado
    0.43
     Dupree
    0.42
     limitado
    0.41
     đựng
    0.41
     affez
    0.40
     omin
    0.39
     sąd
    0.39
     llamado
    0.38
     niedrig
    0.38
     funktion
    0.38
    POSITIVE LOGITS
    <0x0D>
    0.63
    wParam
    0.49
    j
    0.49
    ون
    0.48
    р
    0.45
    [
    0.45
    GLUT
    0.44
    2
    0.44
    </h1>
    0.44
    d
    0.43
    Act Density 0.003%

    No Known Activations