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

    Neuronpedia

    INDEX
    Explanations

    "//"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Net
    -0.06
    SV
    -0.06
     facilities
    -0.06
    Roll
    -0.06
     rak
    -0.06
    /cs
    -0.06
     archae
    -0.06
    xDE
    -0.06
     SG
    -0.06
     Dialogue
    -0.06
    POSITIVE LOGITS
    //↵
    0.07
    erior
    0.07
     merak
    0.07
    ρώ
    0.07
    频
    0.07
    یستم
    0.07
     Yeni
    0.07
    yní
    0.07
    ービス
    0.06
    ником
    0.06
    Act Density 0.001%

    No Known Activations