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
    ssp
    -0.08
     đỏ
    -0.07
    Bed
    -0.06
    (access
    -0.06
     Exit
    -0.06
    заб
    -0.06
    شر
    -0.06
     Hunt
    -0.06
     Shaw
    -0.06
    	date
    -0.06
    POSITIVE LOGITS
    %"
    0.06
     Emb
    0.06
     روسیه
    0.06
    Cro
    0.06
     ČR
    0.06
    CurrentValue
    0.06
     armour
    0.06
    .published
    0.06
    ****************************************************************************
    0.06
     olmadığı
    0.06
    Act Density 0.198%

    No Known Activations