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

    Neuronpedia

    INDEX
    Explanations

    dialogue lines data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    บน
    0.94
    un
    0.91
     dalam
    0.80
    ěné
    0.79
    šnje
    0.78
    fony
    0.77
    COMING
    0.77
    isotropic
    0.76
     quedó
    0.76
    EN
    0.75
    POSITIVE LOGITS
     비해
    0.78
     bors
    0.78
     trypt
    0.74
     enqu
    0.73
     ageing
    0.70
     ogran
    0.70
     meagre
    0.70
     fibres
    0.69
    叱
    0.69
     ques
    0.68
    Act Density 0.002%

    No Known Activations