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 floating-point numbers (numeric tokens containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    utations
    -0.07
     integr
    -0.06
    ์เพ
    -0.06
    olumbia
    -0.06
    _F
    -0.06
    allee
    -0.06
     gerekmektedir
    -0.06
    Coin
    -0.06
     关
    -0.06
    __.__
    -0.06
    POSITIVE LOGITS
     FontWeight
    0.07
    setWidth
    0.06
    StartTime
    0.06
     الثانية
    0.06
    touch
    0.06
    /Table
    0.06
     THEY
    0.06
    instances
    0.06
     Horizontal
    0.06
    ोन
    0.06
    Act Density 0.008%

    No Known Activations