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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Server
    -0.07
     Canter
    -0.06
    	ax
    -0.06
     Beth
    -0.06
     연구
    -0.06
     robber
    -0.06
     forty
    -0.06
    _accepted
    -0.06
     عب
    -0.06
    +f
    -0.06
    POSITIVE LOGITS
    elopment
    0.07
    ічна
    0.07
    profits
    0.07
    .Scan
    0.07
    onyms
    0.06
    .PIPE
    0.06
    iran
    0.06
    糖
    0.06
     Paging
    0.06
    IMPLIED
    0.06
    Act Density 0.014%

    No Known Activations