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

    Neuronpedia

    INDEX
    Explanations

    collective or collectivism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.95
     you
    0.85
    𝙤
    0.84
    ل
    0.82
    you
    0.81
    funds
    0.80
    $
    0.79
    oc
    0.78
    ３
    0.78
    oj
    0.75
    POSITIVE LOGITS
     collective
    1.28
     Collective
    1.13
    collective
    0.96
    Collective
    0.88
     collett
    0.83
    集体
    0.77
    ش
    0.77
     सामूहिक
    0.77
    شون
    0.75
     collectively
    0.75
    Act Density 0.004%

    No Known Activations