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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gn
    -0.07
    *sin
    -0.06
    mu
    -0.06
    yaml
    -0.06
     cade
    -0.06
     cuid
    -0.06
    attrib
    -0.06
     hearty
    -0.06
     '-'
    -0.06
    CID
    -0.06
    POSITIVE LOGITS
    .Black
    0.07
     الأمر
    0.06
    Tele
    0.06
    ">'↵
    0.06
    Utils
    0.06
     ("-
    0.06
    Sdk
    0.06
    (numbers
    0.06
     الجام
    0.06
    (-(
    0.06
    Act Density 0.000%

    No Known Activations