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

    Neuronpedia

    INDEX
    Explanations

    Mentions of years

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect the prepositional “for” when it introduces purposes or time‐related phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Guatemala
    -0.07
    SFML
    -0.07
    .location
    -0.07
     مجموع
    -0.06
     fred
    -0.06
     descripcion
    -0.06
     початку
    -0.06
    .xy
    -0.06
     İz
    -0.06
    Tween
    -0.06
    POSITIVE LOGITS
    erca
    0.06
     innov
    0.06
    φαρ
    0.06
    一些
    0.06
    lim
    0.06
    机会
    0.06
    (optional
    0.06
     Innov
    0.06
    emaakt
    0.06
    ）。
    0.06
    Act Density 0.028%

    No Known Activations