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

    Neuronpedia

    INDEX
    Explanations

    linear progression, combination, algebra, way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    െ
    0.89
    ות
    0.89
    mdash
    0.81
     munitions
    0.80
    as
    0.79
    ت
    0.78
    heiten
    0.77
     investigador
    0.76
     AGN
    0.75
    anu
    0.74
    POSITIVE LOGITS
     gotta
    1.02
    לה
    0.85
    း
    0.81
    existent
    0.80
     guida
    0.79
     holy
    0.79
     Pendidikan
    0.78
    ك
    0.77
     conseguenza
    0.75
     inseparable
    0.75
    Act Density 0.096%

    No Known Activations