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

    Neuronpedia

    INDEX
    Explanations

    a high

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    argmin
    0.74
    istatic
    0.71
    subsetneq
    0.71
    overleftarrow
    0.67
     minifyEnabled
    0.66
    Bottom
    0.65
     менее
    0.65
     Smaller
    0.65
    減少
    0.64
    myButtons
    0.64
    POSITIVE LOGITS
     high
    5.41
    high
    4.99
    High
    4.64
     higher
    4.52
     High
    4.47
     yüksek
    4.29
    高
    4.14
     tinggi
    4.09
    higher
    4.08
     उच्च
    4.03
    Act Density 1.656%

    No Known Activations