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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sí
    -0.07
    carrier
    -0.07
    、何
    -0.06
    érica
    -0.06
    Good
    -0.06
    ului
    -0.06
    -person
    -0.06
    nut
    -0.06
    Ether
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Nex
    0.07
     CommandLine
    0.06
     Dünya
    0.06
    chedule
    0.06
     ряд
    0.06
     phoneNumber
    0.06
     getY
    0.06
    轻
    0.06
    _cache
    0.06
     slender
    0.06
    Act Density 0.011%

    No Known Activations