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

    Neuronpedia

    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heb
    -0.07
     Flavor
    -0.06
    ♀
    -0.06
     thereof
    -0.06
    ��
    -0.06
    INCLUDE
    -0.06
    .getWriter
    -0.06
     flawed
    -0.06
    edral
    -0.06
     setPassword
    -0.06
    POSITIVE LOGITS
    脱
    0.07
    」↵↵
    0.07
    (ship
    0.06
     instances
    0.06
    73
    0.06
     QT
    0.06
     surplus
    0.06
     bölge
    0.06
    ्ज
    0.06
    /ad
    0.06
    Act Density 0.070%

    No Known Activations