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

    Neuronpedia

    INDEX
    Explanations

    Okay ## QR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nebude
    0.44
     mismas
    0.40
     vanno
    0.38
     biais
    0.38
     terão
    0.37
     mismos
    0.37
     uso
    0.36
     stesse
    0.36
     gyro
    0.36
     conséquences
    0.36
    POSITIVE LOGITS
    There
    0.43
    Chemical
    0.41
    题目
    0.40
    While
    0.39
    World
    0.39
    ujourd
    0.38
    The
    0.38
    title
    0.38
    When
    0.38
     prachtige
    0.38
    Act Density 0.330%

    No Known Activations