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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Addition
    -0.07
     чер
    -0.06
    berger
    -0.06
    imes
    -0.06
     microscope
    -0.06
     тов
    -0.06
     magnet
    -0.06
     роботу
    -0.06
     جمع
    -0.06
    ิบ
    -0.06
    POSITIVE LOGITS
    oref
    0.08
    /math
    0.06
    Br
    0.06
     Ngb
    0.06
    .getInput
    0.06
    @Configuration
    0.06
    /sys
    0.06
    +Sans
    0.06
     arguments
    0.06
     العامة
    0.06
    Act Density 0.061%

    No Known Activations