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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thinkable
    -0.07
    }->{
    -0.07
    partment
    -0.06
    一流的
    -0.06
    Unity
    -0.06
    (Current
    -0.06
    邺
    -0.06
    nahme
    -0.06
    Fac
    -0.06
     cloak
    -0.06
    POSITIVE LOGITS
    يري
    0.07
    科技进步
    0.07
    (dt
    0.07
    ицы
    0.07
    告知
    0.07
    和技术
    0.07
    IDL
    0.07
    isé
    0.07
     academics
    0.07
    raising
    0.07
    Act Density 0.047%

    No Known Activations