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

    Neuronpedia

    INDEX
    Explanations

    common word pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Even
    0.34
    even
    0.32
    '
    0.32
    with
    0.32
    -_
    0.31
     Even
    0.31
    rible
    0.31
    This
    0.30
    In
    0.29
    ger
    0.29
    POSITIVE LOGITS
     endothelial
    0.40
     gastroenter
    0.39
    <unused494>
    0.38
     surfactants
    0.38
    <unused313>
    0.38
    <unused1827>
    0.37
     lithium
    0.36
     radiotherapy
    0.36
    <unused472>
    0.36
     bestimmte
    0.36
    Act Density 0.020%

    No Known Activations