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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric or ordinal references in game titles and edition/version indicators (e.g. sequel numbers, “PS4,” “1.5,” “first,” “three,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ald
    -0.07
    uzu
    -0.07
    mít
    -0.06
    $x
    -0.06
    90
    -0.06
     định
    -0.06
    rab
    -0.06
     sauce
    -0.06
    arga
    -0.06
    stro
    -0.06
    POSITIVE LOGITS
    .Delay
    0.07
    _UPLOAD
    0.06
    ImGui
    0.06
     dislikes
    0.06
    .weapon
    0.06
    .IGNORE
    0.06
    .groupControl
    0.06
     Soc
    0.06
    保
    0.06
     sä
    0.06
    Act Density 0.038%

    No Known Activations