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

    Neuronpedia

    INDEX
    Explanations

    [

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eer
    1.16
    een
    1.14
    тную
    0.99
    o
    0.93
    ej
    0.93
    iq
    0.89
    aar
    0.88
    iology
    0.86
    ea
    0.85
    oak
    0.84
    POSITIVE LOGITS
     пред
    0.89
    Дата
    0.87
    С
    0.84
    ص
    0.84
     начало
    0.82
    נ
    0.82
    к
    0.81
     بادشاہ
    0.80
    ਸ
    0.79
    🧛
    0.78
    Act Density 0.002%

    No Known Activations