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

    Neuronpedia

    INDEX
    Explanations

    creating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pensar
    -0.07
    junction
    -0.07
    	So
    -0.07
    ModelAttribute
    -0.07
    �
    -0.07
    -par
    -0.07
    	parameters
    -0.07
    .Attributes
    -0.07
     a
    -0.06
     which
    -0.06
    POSITIVE LOGITS
     Tacoma
    0.06
    işleri
    0.06
     包
    0.06
    اجع
    0.06
     오후
    0.06
     тро
    0.06
     opioid
    0.06
     ống
    0.05
    िड
    0.05
    ωτερ
    0.05
    Act Density 0.384%

    No Known Activations