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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	order
    -0.07
    Entry
    -0.06
    anan
    -0.06
     seven
    -0.06
     Steph
    -0.06
    March
    -0.06
    几个
    -0.06
    MO
    -0.06
     ROOM
    -0.06
     ثلاث
    -0.06
    POSITIVE LOGITS
    _encode
    0.07
    titre
    0.07
    จาก
    0.06
     Estimated
    0.06
    Normals
    0.06
     Sa
    0.06
     нас
    0.06
    grounds
    0.06
     Treatment
    0.06
     DOE
    0.06
    Act Density 0.010%

    No Known Activations