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

    Neuronpedia

    INDEX
    Explanations

    vary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uem
    -0.08
    nard
    -0.07
     kone
    -0.07
    慈善
    -0.07
     Buen
    -0.07
    篓
    -0.07
    首款
    -0.07
    肯定是
    -0.07
    -saving
    -0.07
     smuggling
    -0.07
    POSITIVE LOGITS
    Գ
    0.07
     conc
    0.07
    ultiple
    0.06
    ออกไป
    0.06
    ############################
    0.06
     portions
    0.06
     paragraphs
    0.06
    Ⓓ
    0.06
    .getRow
    0.06
    createView
    0.06
    Act Density 0.007%

    No Known Activations