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

    Neuronpedia

    INDEX
    Explanations

    about: andOmertà

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beteil
    0.98
     Taken
    0.93
    กด
    0.92
    橥
    0.91
     Silicon
    0.90
    ング
    0.90
     HomeScreen
    0.89
    ة
    0.87
     соль
    0.86
    نم
    0.86
    POSITIVE LOGITS
     equidistant
    1.18
     usl
    1.06
    тельство
    1.02
    aleb
    1.01
     evenly
    1.01
    Cette
    1.01
    ર
    0.98
    kring
    0.97
    ꜰ
    0.97
     già
    0.96
    Act Density 0.018%

    No Known Activations