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

    Neuronpedia

    INDEX
    Explanations

    measurements and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IVITY
    0.82
     kä
    0.81
     titel
    0.80
     ге
    0.78
     Parti
    0.78
     vũ
    0.76
    毘
    0.76
     OF
    0.75
     sacrament
    0.75
     mulai
    0.75
    POSITIVE LOGITS
    Стра
    0.86
     prostu
    0.76
    でした
    0.75
     structurally
    0.72
    ഷണ
    0.72
    craft
    0.72
    裕
    0.71
    Ϲ
    0.71
    Sett
    0.71
    Շ
    0.71
    Act Density 0.000%

    No Known Activations