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

    Neuronpedia

    INDEX
    Explanations

    relaxing and having fun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YOUR
    -0.07
     reminiscent
    -0.06
    برای
    -0.06
    Location
    -0.06
     Blind
    -0.06
     preprocess
    -0.06
    board
    -0.06
     部
    -0.06
    ﾟ
    -0.06
    τικός
    -0.06
    POSITIVE LOGITS
    _FB
    0.08
    )])↵↵
    0.07
    فع
    0.06
    ?>/
    0.06
     кг
    0.06
    ]])↵↵
    0.06
    ))),↵
    0.06
     cha
    0.06
    rition
    0.06
    ")]↵↵
    0.06
    Act Density 0.110%

    No Known Activations