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

    Neuronpedia

    INDEX
    Explanations

    Python lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ORK
    -0.07
    currentUser
    -0.07
    .company
    -0.07
     chubby
    -0.07
     scorer
    -0.07
    -Americans
    -0.07
    .Minimum
    -0.07
    .ORDER
    -0.06
    ẩn
    -0.06
    荸
    -0.06
    POSITIVE LOGITS
    _particle
    0.08
     tegen
    0.07
    .codec
    0.07
    Socket
    0.07
     scala
    0.07
    screen
    0.07
     locking
    0.07
    方便
    0.07
    🔷
    0.07
     [];↵
    0.06
    Act Density 0.167%

    No Known Activations