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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рід
    -0.07
     Stacy
    -0.07
    		  ↵
    -0.06
     Evans
    -0.06
     humane
    -0.06
    agal
    -0.06
     možná
    -0.06
    getRow
    -0.06
    hatt
    -0.06
     Ты
    -0.06
    POSITIVE LOGITS
    мини
    0.07
     Buffered
    0.06
     Bio
    0.06
     Decor
    0.06
    important
    0.06
     continual
    0.06
    charged
    0.06
    ività
    0.06
     IG
    0.06
     initiative
    0.06
    Act Density 0.001%

    No Known Activations