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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scenes
    -0.08
    	task
    -0.07
    Compet
    -0.06
     Cloth
    -0.06
     maths
    -0.06
     Views
    -0.06
     Dias
    -0.06
    Blo
    -0.06
     polygon
    -0.06
     Conte
    -0.06
    POSITIVE LOGITS
     roleName
    0.07
    
    0.06
     Norway
    0.06
     gridColumn
    0.06
    ỡ
    0.06
     polish
    0.06
    -human
    0.06
    -party
    0.06
     Lan
    0.06
     numpy
    0.06
    Act Density 0.000%

    No Known Activations