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

    Neuronpedia

    INDEX
    Explanations

    green jungle, airbnb app

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.44
     принято
    0.44
    福祉
    0.44
    ylie
    0.43
     つ
    0.43
    yle
    0.43
    的消息
    0.43
    くちゃ
    0.42
    untansi
    0.42
     گے
    0.41
    POSITIVE LOGITS
    ش
    0.55
    తో
    0.53
     Ens
    0.52
     Brandenburg
    0.52
     Tre
    0.52
     Progression
    0.52
    峒
    0.50
    禟
    0.50
     Smell
    0.50
     Trapez
    0.50
    Act Density 0.001%

    No Known Activations