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

    Neuronpedia

    INDEX
    Explanations

    action completed, followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alış
    0.27
     dotycz
    0.26
     çant
    0.25
     équipements
    0.25
     নিজেকে
    0.25
     እድ
    0.25
    ANDEZ
    0.25
     учет
    0.25
     mám
    0.24
     noastră
    0.24
    POSITIVE LOGITS
     in
    0.38
     by
    0.36
    by
    0.33
     on
    0.32
     with
    0.30
    ，
    0.30
    at
    0.29
     from
    0.29
    in
    0.29
     at
    0.27
    Act Density 0.204%

    No Known Activations