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

    Neuronpedia

    INDEX
    Explanations

    area on the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.52
    Idaho
    0.51
     engineering
    0.48
     ENGINEERING
    0.47
    STRUCT
    0.46
    كتب
    0.46
    $(
    0.44
     Idaho
    0.44
     organisational
    0.43
     STRU
    0.42
    POSITIVE LOGITS
     ഇൻ
    0.50
     ہماری
    0.49
     ชุด
    0.48
     nossa
    0.46
    ইন
    0.46
    assignmentItems
    0.45
     বরং
    0.45
     پت
    0.45
    媢
    0.45
     mindful
    0.44
    Act Density 0.001%

    No Known Activations