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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of teams winning or champions of specific divisions or regional zones (e.g. “winners of the East/West division”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Remix
    -0.08
     fus
    -0.06
    �
    -0.06
     obligations
    -0.06
    кових
    -0.06
    ="<?=$
    -0.06
    ид
    -0.06
    pig
    -0.06
    -make
    -0.06
     capitalism
    -0.06
    POSITIVE LOGITS
    crease
    0.08
    [train
    0.06
     */
↵
↵
    0.06
    (Exception
    0.06
    IND
    0.06
    Ground
    0.06
     trance
    0.06
    BACKGROUND
    0.06
     SizedBox
    0.06
    (metadata
    0.06
    Act Density 0.010%

    No Known Activations