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

    Neuronpedia

    INDEX
    Explanations

    victory

    np_max-act · gemini-2.0-flash

    The neuron activates on sports match outcome phrases—particularly words like “win” or “victory” together with the numeric score details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Huang
    -0.07
     rampage
    -0.06
     balance
    -0.06
    ыва
    -0.06
    _ACCEPT
    -0.06
    bz
    -0.06
    /arm
    -0.06
     Sharon
    -0.06
    Atoms
    -0.06
    CHA
    -0.06
    POSITIVE LOGITS
     حی
    0.07
    −
    0.07
    줄
    0.06
    .Horizontal
    0.06
     clickable
    0.06
    گذ
    0.06
    $model
    0.06
     Leipzig
    0.06
     واست
    0.06
     qty
    0.06
    Act Density 0.017%

    No Known Activations