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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     walmart
    -0.07
    �
    -0.06
    coll
    -0.06
     Robert
    -0.06
     Eth
    -0.06
     Sandra
    -0.06
     Gary
    -0.06
    .y
    -0.06
    Eth
    -0.06
     Saudis
    -0.05
    POSITIVE LOGITS
     했다
    0.07
    оск
    0.06
     StringUtils
    0.06
    Arrow
    0.06
    μά
    0.06
    ristol
    0.06
     Barang
    0.06
    _exist
    0.06
    _Order
    0.06
    804
    0.06
    Act Density 0.070%

    No Known Activations