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

    Neuronpedia

    INDEX
    Explanations

    everyone/everybody

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ann
    -0.07
     nebo
    -0.07
     Description
    -0.06
     buff
    -0.06
    زمان
    -0.06
     arranging
    -0.06
     Went
    -0.06
    welcome
    -0.06
     paired
    -0.06
    няется
    -0.06
    POSITIVE LOGITS
     DAL
    0.08
    (decimal
    0.07
    yyval
    0.06
     vocab
    0.06
    )},↵
    0.06
    ForObject
    0.06
    *num
    0.06
    -нибудь
    0.06
    	camera
    0.06
    (tv
    0.06
    Act Density 0.003%

    No Known Activations