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

    Neuronpedia

    INDEX
    Explanations

    ruin, disrupt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fire
    -0.07
     Proxy
    -0.07
     тебя
    -0.07
     půl
    -0.07
    โจ
    -0.07
     Brewers
    -0.07
    夜
    -0.07
    ワー
    -0.06
     einen
    -0.06
    歐
    -0.06
    POSITIVE LOGITS
    _RX
    0.06
    Alex
    0.06
    crc
    0.06
    abled
    0.06
     cancelButton
    0.06
    aur
    0.06
    Lite
    0.06
     Rogue
    0.06
    (clicked
    0.05
    sex
    0.05
    Act Density 0.186%

    No Known Activations