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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    This neuron spotlights lines that present software version numbers paired with a slash and release date (e.g. “2.6.8 / 2017-05-18”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -src
    -0.06
    Β
    -0.06
     following
    -0.06
     kepada
    -0.06
    -find
    -0.06
    �
    -0.05
     hver
    -0.05
     lief
    -0.05
    cripcion
    -0.05
    wnd
    -0.05
    POSITIVE LOGITS
     года
    0.07
    ▋
    0.07
    î
    0.06
    serious
    0.06
    \widgets
    0.06
     Produkt
    0.06
     Serious
    0.06
    whereIn
    0.06
    grim
    0.06
    >>::
    0.06
    Act Density 0.003%

    No Known Activations