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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objectId
    -0.07
    telefone
    -0.07
    pared
    -0.07
    plet
    -0.07
    ResponseBody
    -0.07
     clientId
    -0.07
     diagnosed
    -0.07
     collapsing
    -0.07
    -tr
    -0.07
    	ip
    -0.07
    POSITIVE LOGITS
    ∎
    0.08
     viện
    0.07
     fy
    0.07
     Gain
    0.07
    冲洗
    0.07
     xấu
    0.07
    묵
    0.07
    轳
    0.07
    時
    0.07
     COST
    0.06
    Act Density 0.001%

    No Known Activations