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

    Neuronpedia

    INDEX
    Explanations

    club

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NASCAR
    0.40
    日本語
    0.39
     Pulitzer
    0.37
    kubectl
    0.37
     অতুল
    0.36
     miliardi
    0.36
    <0xAA>
    0.36
     दुनियाभर
    0.36
    妊娠
    0.35
     billionaire
    0.35
    POSITIVE LOGITS
     club
    0.80
     clubs
    0.73
     klub
    0.70
     clubes
    0.68
    club
    0.68
     juniors
    0.66
     Clubs
    0.65
     клуба
    0.65
     tournaments
    0.64
     junior
    0.64
    Act Density 0.011%

    No Known Activations