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

    Neuronpedia

    INDEX
    Explanations

    since then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    া
    2.10
    ا
    2.02
     Certainly
    1.98
    ीन
    1.87
    a
    1.87
    ी
    1.83
    ुक्त
    1.71
    們
    1.70
    ु
    1.70
    ן
    1.69
    POSITIVE LOGITS
     inception
    1.82
    IZONTAL
    1.64
    с
    1.59
     childhood
    1.58
    ح
    1.53
    ע
    1.45
     luego
    1.44
     hace
    1.41
    ../../
    1.37
    ദ
    1.34
    Act Density 0.009%

    No Known Activations