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

    Neuronpedia

    INDEX
    Explanations

    in/near

    np_max-act · gemini-2.0-flash

    This neuron fires on the preposition “in” when it introduces a specific date, year, or other numeric/time expression.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    νου
    -0.07
    Europe
    -0.06
     Erotic
    -0.06
     march
    -0.06
     yılında
    -0.06
    sWith
    -0.06
     sexuality
    -0.06
    _room
    -0.06
    +)\
    -0.06
    dou
    -0.06
    POSITIVE LOGITS
    -f
    0.07
    ΟΦ
    0.06
    part
    0.06
     vyjád
    0.06
     referencedColumnName
    0.06
    ">'.
    0.06
    <Action
    0.06
     mucho
    0.06
    대학
    0.06
     Clar
    0.06
    Act Density 0.040%

    No Known Activations