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

    Neuronpedia

    INDEX
    Explanations

    use bash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ad
    0.60
     acte
    0.58
     aw
    0.58
     notification
    0.58
    افل
    0.57
    明顯
    0.56
     rep
    0.56
     curNode
    0.55
    arto
    0.55
     flock
    0.55
    POSITIVE LOGITS
     Ellison
    0.65
    Singleton
    0.63
    commission
    0.60
     Hey
    0.60
    ణా
    0.60
    HEY
    0.60
    sburg
    0.60
    sac
    0.59
    HTML
    0.59
     लेट्स
    0.59
    Act Density 0.191%

    No Known Activations