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

    Neuronpedia

    INDEX
    Explanations

    score

    np_max-act · gemini-2.0-flash

    The neuron fires on terms describing runners advancing or scoring events (e.g. “scored,” “advance,” “RBI,” “stranding”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    った
    -0.06
    ()
↵
↵
↵
    -0.06
    6
    -0.06
    ;
↵
↵
↵
    -0.06
    .fix
    -0.06
    .Build
    -0.06
     возраста
    -0.06
    910
    -0.06
    .$
    -0.06
    vý
    -0.06
    POSITIVE LOGITS
     İzmir
    0.06
     YAML
    0.06
     Diabetes
    0.06
     yık
    0.06
    哲
    0.06
    .ST
    0.06
    .EntityFramework
    0.06
     quaternion
    0.06
    _ATTRIB
    0.06
     DATABASE
    0.06
    Act Density 0.001%

    No Known Activations