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

    Neuronpedia

    INDEX
    Explanations

    Designated drivers/avoid drunk driving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wpływ
    -0.08
    捩
    -0.07
     NodeList
    -0.07
    nes
    -0.07
     carne
    -0.07
    _FOR
    -0.07
    隽
    -0.07
    rne
    -0.07
     Squadron
    -0.06
    .leadingAnchor
    -0.06
    POSITIVE LOGITS
    直播
    0.09
    操
    0.08
    찯
    0.07
    клад
    0.07
    봇
    0.07
     שכבר
    0.07
    closest
    0.06
     وما
    0.06
     UL
    0.06
     collaborating
    0.06
    Act Density 0.009%

    No Known Activations