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

    Neuronpedia

    INDEX
    Explanations

    technical answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patches
    -0.07
    自分の
    -0.06
    ในส
    -0.06
    ConnectionString
    -0.06
    posting
    -0.06
    fit
    -0.06
    	fp
    -0.06
     bilm
    -0.06
    vol
    -0.06
    -Apr
    -0.06
    POSITIVE LOGITS
     Seg
    0.07
     Rhe
    0.07
     Nay
    0.06
     Jug
    0.06
     وح
    0.06
    (end
    0.06
     kak
    0.06
     věku
    0.06
    NEXT
    0.06
     Jackson
    0.06
    Act Density 0.092%

    No Known Activations