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

    Neuronpedia

    INDEX
    Explanations

    close

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     around
    1.42
     Around
    1.36
    around
    1.32
    Around
    1.30
     alrededor
    1.21
     autour
    1.16
     حول
    1.13
     intorno
    1.09
     rundt
    1.06
     kolem
    1.05
    POSITIVE LOGITS
    近
    0.70
    近い
    0.63
     close
    0.62
     however
    0.58
    却
    0.56
     Close
    0.55
     однако
    0.54
    Close
    0.54
     gần
    0.54
    however
    0.54
    Act Density 0.001%

    No Known Activations