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

    Neuronpedia

    INDEX
    Explanations

    son

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric values (decimal numbers) embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     roam
    -0.07
    Focused
    -0.07
    Channels
    -0.06
     custom
    -0.06
     broker
    -0.06
     accomplished
    -0.06
     Mara
    -0.06
    _CONNECT
    -0.06
     mature
    -0.06
    ELEMENT
    -0.06
    POSITIVE LOGITS
    �
    0.08
     firepower
    0.07
     Econ
    0.07
     QVector
    0.06
    lamaz
    0.06
    まま
    0.06
     韓
    0.06
    학
    0.06
    韓
    0.06
     طور
    0.06
    Act Density 0.001%

    No Known Activations