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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    appropriate
    -0.07
     cuanto
    -0.07
    >",↵
    -0.07
     customize
    -0.07
    _Global
    -0.07
    onna
    -0.06
    traction
    -0.06
    _insert
    -0.06
    ']↵↵
    -0.06
     qui
    -0.06
    POSITIVE LOGITS
     boj
    0.06
     आद
    0.06
     इसम
    0.06
     interrupts
    0.06
    perienced
    0.06
     dní
    0.06
     roleId
    0.05
    OfMonth
    0.05
    итися
    0.05
    _kelas
    0.05
    Act Density 0.012%

    No Known Activations