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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash

    This neuron detects language that offers something “as a starting point,” i.e. suggestion phrases like “as a starting point.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gas
    -0.08
     bearer
    -0.07
     gases
    -0.07
    งหมด
    -0.06
    {_
    -0.06
     Ministers
    -0.06
     susp
    -0.06
    ายน
    -0.06
    Off
    -0.06
     performs
    -0.06
    POSITIVE LOGITS
     */
↵
↵
    0.06
     quantitative
    0.06
    IXEL
    0.06
    _Price
    0.06
    μπ
    0.06
    =<?
    0.06
    akter
    0.06
    _todo
    0.06
    _dates
    0.06
    ोख
    0.06
    Act Density 0.010%

    No Known Activations