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

    Neuronpedia

    INDEX
    Explanations

    lists and dictionaries

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (decimal numbers in code).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ümüş
    -0.07
    บอล
    -0.07
    -desktop
    -0.07
    ▲
    -0.06
    Ah
    -0.06
    ánh
    -0.06
    pios
    -0.06
     Hồ
    -0.06
     Alley
    -0.06
    alley
    -0.06
    POSITIVE LOGITS
     dispers
    0.07
    _INSERT
    0.06
     dict
    0.06
     pretty
    0.06
    (setq
    0.06
     sut
    0.06
    crc
    0.06
     deque
    0.06
     inertia
    0.06
    .ToBoolean
    0.06
    Act Density 0.009%

    No Known Activations