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

    Neuronpedia

    INDEX
    Explanations

    positional prepositions after nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     występu
    -1.20
     placed
    -1.19
     located
    -1.17
     parked
    -1.10
     newly
    -1.09
     installed
    -1.08
     präsenti
    -1.07
     stationed
    -1.06
     put
    -1.04
     położ
    -1.03
    POSITIVE LOGITS
     into
    2.52
     onto
    2.34
     in
    1.97
     on
    1.92
     alongside
    1.48
    onto
    1.34
     inside
    1.24
     across
    1.19
     along
    1.16
    into
    1.16
    Act Density 0.260%

    No Known Activations