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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates on terms that specify numeric counts or sizes (e.g., “number,” “queries,” “size,” “operations”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     když
    -0.06
     haunting
    -0.06
    ňování
    -0.06
    reminder
    -0.06
    Rgb
    -0.06
    Bang
    -0.06
    Clip
    -0.06
    委员
    -0.06
     postpon
    -0.06
    Margins
    -0.06
    POSITIVE LOGITS
     constituency
    0.07
    ierre
    0.07
     typeId
    0.06
    icts
    0.06
    edb
    0.06
     accurately
    0.06
     створю
    0.06
     elephant
    0.06
     softball
    0.06
     xn
    0.06
    Act Density 0.063%

    No Known Activations