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

    Neuronpedia

    INDEX
    Explanations

    Faces wake up actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unequal
    -0.07
    /board
    -0.07
    起
    -0.07
     bridge
    -0.07
     Mean
    -0.07
    sweet
    -0.06
     XXX
    -0.06
    _Image
    -0.06
     عليها
    -0.06
    Level
    -0.06
    POSITIVE LOGITS
    endars
    0.07
    +f
    0.06
    %
↵
    0.06
    ün
    0.06
    �
    0.06
     deb
    0.06
     sendData
    0.06
    เทศ
    0.06
    /private
    0.06
    prototype
    0.06
    Act Density 0.135%

    No Known Activations