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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inteira
    -0.09
    天下
    -0.08
     Aufwand
    -0.08
    verstanden
    -0.08
     ખર્ચ
    -0.07
     мөл
    -0.07
     квали
    -0.07
     практике
    -0.07
     Lesbian
    -0.07
     qualitat
    -0.07
    POSITIVE LOGITS
     sturdy
    0.09
     vibrant
    0.09
     softness
    0.09
     serene
    0.08
    纹
    0.08
    软
    0.08
     lively
    0.08
     colorful
    0.08
     kuch
    0.08
     soft
    0.08
    Act Density 0.010%

    No Known Activations