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

    Neuronpedia

    INDEX
    Explanations

    activism and advocacy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डाउट
    0.66
     성능
    0.64
     grinned
    0.64
     glanced
    0.62
     capricious
    0.57
     glances
    0.57
     windings
    0.56
     overfitting
    0.56
     soddis
    0.55
     कंफ
    0.55
    POSITIVE LOGITS
     advocacy
    2.73
     advocating
    2.45
     campaigning
    2.41
     Advocacy
    2.41
     advocate
    2.30
     activism
    2.27
     advocates
    2.16
     advocated
    2.02
     campaign
    1.99
     campaigns
    1.99
    Act Density 0.309%

    No Known Activations