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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leth
    -0.07
    ريس
    -0.07
     sheep
    -0.07
     modeling
    -0.07
    ʕ
    -0.07
     صحيح
    -0.07
    了很多
    -0.07
    StringEncoding
    -0.07
     flashy
    -0.07
    btc
    -0.07
    POSITIVE LOGITS
    0.08
    _notice
    0.07
    Modifiers
    0.07
    кон
    0.07
    .groupBox
    0.07
    いただく
    0.07
     zwe
    0.07
    0.06
    Flex
    0.06
    SourceType
    0.06
    Act Density 0.005%

    No Known Activations