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

    Neuronpedia

    INDEX
    Explanations

    two-dimensional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ато
    0.44
     سور
    0.40
     單
    0.39
     jednot
    0.38
     单
    0.38
    entin
    0.37
     എ
    0.37
    inoa
    0.37
    ონის
    0.37
    孤
    0.37
    POSITIVE LOGITS
     dimensional
    0.85
    dimensional
    0.81
    Dimensional
    0.80
     Dimensional
    0.69
    imensional
    0.63
    Way
    0.62
     sided
    0.60
     way
    0.58
    way
    0.58
     Way
    0.56
    Act Density 0.014%

    No Known Activations