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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    礼
    -0.07
     manifested
    -0.07
    dw
    -0.06
     PIE
    -0.06
     oral
    -0.06
    [var
    -0.06
     Scrap
    -0.06
     Combo
    -0.06
     Hussein
    -0.06
     Checker
    -0.06
    POSITIVE LOGITS
     mongoose
    0.06
    inant
    0.06
    buff
    0.06
     ByteString
    0.06
    енты
    0.06
    buster
    0.06
     اه
    0.06
     dma
    0.06
    -static
    0.06
     siyasi
    0.06
    Act Density 0.002%

    No Known Activations