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

    Neuronpedia

    INDEX
    Explanations

    sports substitutions

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of player substitutions (e.g. “X came on for Y,” “introduced ___,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     PW
    -0.07
    /Card
    -0.07
    SEN
    -0.07
    -Pack
    -0.07
    맹
    -0.06
     Máy
    -0.06
     SHR
    -0.06
    Mount
    -0.06
     APIs
    -0.06
     Btn
    -0.06
    POSITIVE LOGITS
    (vertices
    0.07
     neglig
    0.07
    (coordinates
    0.07
    %">↵
    0.07
    .expires
    0.07
    =/
    0.07
     jeans
    0.06
    .Graph
    0.06
    .graph
    0.06
    =str
    0.06
    Act Density 0.004%

    No Known Activations