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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ranges
    -0.07
    RF
    -0.07
    _real
    -0.07
     Rox
    -0.06
     ramp
    -0.06
    毕业
    -0.06
     �
    -0.06
     fathers
    -0.06
     URLs
    -0.06
    озем
    -0.06
    POSITIVE LOGITS
    _TestCase
    0.07
    ||(
    0.06
    exam
    0.06
     varsa
    0.06
     hakkı
    0.06
    CATEGORY
    0.06
    .dr
    0.06
     стоимость
    0.06
    >{{
    0.06
    카라
    0.06
    Act Density 0.114%

    No Known Activations