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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens (especially decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     troop
    -0.07
    �
    -0.07
     له
    -0.07
     полез
    -0.07
     CancellationToken
    -0.06
     persec
    -0.06
     Liu
    -0.06
    set
    -0.06
     Nếu
    -0.06
     dap
    -0.06
    POSITIVE LOGITS
    qq
    0.07
     complimentary
    0.07
    icho
    0.06
     FILES
    0.06
     specialised
    0.06
    важа
    0.06
    utter
    0.06
    qw
    0.06
     Special
    0.06
    ])-
    0.06
    Act Density 0.001%

    No Known Activations