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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    attering
    -0.06
     đãi
    -0.06
     petals
    -0.06
     spotlight
    -0.06
     центр
    -0.06
    人
    -0.06
    roads
    -0.06
    bery
    -0.06
     warranted
    -0.06
    ุย
    -0.06
    POSITIVE LOGITS
    Cl
    0.08
    ____________
    0.08
     PE
    0.07
     ui
    0.07
     avis
    0.07
     recib
    0.06
    	ns
    0.06
    ==============
    0.06
    (item
    0.06
    '}
    0.06
    Act Density 0.000%

    No Known Activations