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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scoring and leads in competitive sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    leading positions and advantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.56
     AssemblyCulture
    -0.44
    BufferException
    -0.41
    Diweddarwch
    -0.38
     uLocal
    -0.38
     ब्रेकडाउन
    -0.35
     ProtoMessage
    -0.35
    Datuak
    -0.34
    (['/
    -0.34
     yen
    -0.34
    POSITIVE LOGITS
    DockStyle
    0.48
     Roskov
    0.46
    lead
    0.45
    Winning
    0.42
    Lead
    0.42
    principalColumn
    0.41
    antd
    0.40
     initialState
    0.40
    Advantage
    0.40
    strip
    0.40
    Act Density 0.058%

    No Known Activations