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

    Neuronpedia

    INDEX
    Explanations

    """

    np_max-act · gemini-2.0-flash

    The neuron detects floating-point numeric literals (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    !:
    -0.07
    ホ
    -0.07
    EMU
    -0.07
    особ
    -0.07
     hari
    -0.06
    ąd
    -0.06
     PART
    -0.06
    scar
    -0.06
    fre
    -0.06
     FAR
    -0.06
    POSITIVE LOGITS
    _general
    0.06
    _y
    0.06
     позд
    0.06
     tầm
    0.06
    approximately
    0.06
     producción
    0.06
     가능
    0.06
    .DoesNotExist
    0.06
     출
    0.06
     Battles
    0.06
    Act Density 0.003%

    No Known Activations