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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ranc
    -0.08
    érieure
    -0.08
    领取
    -0.08
    实际上
    -0.08
     Dienste
    -0.08
    회사
    -0.08
     purported
    -0.08
    왔다
    -0.08
    IDL
    -0.07
     Welt
    -0.07
    POSITIVE LOGITS
     красив
    0.08
    五
    0.08
     Innovation
    0.08
    innovation
    0.08
    alpha
    0.08
    Innovation
    0.07
     चिक
    0.07
     جميلة
    0.07
     aesthetics
    0.07
     Josh
    0.07
    Act Density 0.001%

    No Known Activations