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

    Neuronpedia

    INDEX
    Explanations

    social

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	template
    -0.07
     tijd
    -0.07
    кін
    -0.07
     point
    -0.07
     elt
    -0.07
    pret
    -0.07
     verst
    -0.07
     pencil
    -0.07
    мит
    -0.07
    pire
    -0.07
    POSITIVE LOGITS
     social
    0.16
     Social
    0.15
    social
    0.12
    Social
    0.11
     SOCIAL
    0.10
     socially
    0.09
     sociale
    0.09
     soc
    0.09
     Soc
    0.08
    -social
    0.08
    Act Density 0.028%

    No Known Activations