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

    Neuronpedia

    INDEX
    Explanations

    President

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sprites
    -0.07
     interactive
    -0.07
    -sk
    -0.07
    -middle
    -0.06
     circle
    -0.06
    onymous
    -0.06
     在
    -0.06
     neighbors
    -0.06
    _activation
    -0.06
     heroic
    -0.06
    POSITIVE LOGITS
     '#{
    0.07
    erc
    0.06
    OOT
    0.06
    지만
    0.06
    Uvs
    0.06
     ACE
    0.06
    onsense
    0.06
     Dahl
    0.06
    男子
    0.06
     Joker
    0.06
    Act Density 0.011%

    No Known Activations