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

    Neuronpedia

    INDEX
    Explanations

    rosis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    replaceAll
    -0.07
    .'<
    -0.07
     layui
    -0.07
    ().'
    -0.07
    =('
    -0.06
    .<
    -0.06
     Bat
    -0.06
    Sou
    -0.06
     Jas
    -0.06
     Zug
    -0.06
    POSITIVE LOGITS
    潜力
    0.08
     destruction
    0.08
    密度
    0.08
     obsession
    0.08
    udent
    0.07
    -down
    0.07
    itates
    0.07
    严重影响
    0.07
     contributor
    0.07
    -more
    0.07
    Act Density 0.000%

    No Known Activations