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

    Neuronpedia

    INDEX
    Explanations

    allowance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Login
    -0.07
    -0.07
    ／
    -0.07
     nutrition
    -0.06
     span
    -0.06
    Chocolate
    -0.06
    _counts
    -0.06
    "c
    -0.06
    LObject
    -0.06
    -0.06
    POSITIVE LOGITS
    BIN
    0.07
     UIEdgeInsets
    0.07
     afterEach
    0.06
     HR
    0.06
    AM
    0.06
     Randy
    0.06
     Ф
    0.06
    ONGLONG
    0.06
    (sock
    0.06
    ち
    0.06
    Act Density 0.037%

    No Known Activations