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

    Neuronpedia

    INDEX
    Explanations

    extending filesystems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⴌ
    0.50
    াঙ্গা
    0.49
     Nawaz
    0.48
    🖉
    0.47
    ঁচু
    0.46
    िवारी
    0.46
     Gippsland
    0.46
    )+"]("+
    0.46
    aisi
    0.45
    跄
    0.45
    POSITIVE LOGITS
     Ext
    0.72
    Ext
    0.72
     extrusion
    0.66
     extr
    0.65
    remely
    0.60
     extinction
    0.59
    ext
    0.58
    extr
    0.57
     ext
    0.55
    2
    0.55
    Act Density 0.007%

    No Known Activations