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

    Neuronpedia

    INDEX
    Explanations

    list formatting/markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    askan
    0.62
     tra
    0.58
     amongst
    0.57
     k
    0.56
    etrotters
    0.55
     di
    0.51
     d
    0.50
    系
    0.49
     m
    0.49
     organics
    0.48
    POSITIVE LOGITS
    <unused1760>
    1.00
    AutorLabel
    0.99
     habe
    0.98
    عند
    0.96
    Legisl
    0.95
    Დ
    0.95
    Erin
    0.95
    。。
    0.94
    Შ
    0.94
    したいと思います
    0.93
    Act Density 1.005%

    No Known Activations