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

    Neuronpedia

    INDEX
    Explanations

    code contexts (SQL, loops, print, connections)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    煅
    0.40
     thermodynam
    0.40
     herringbone
    0.39
     wrink
    0.39
    Những
    0.39
    LPTMR
    0.38
     anhyd
    0.38
     MPa
    0.38
     enzim
    0.38
     glycer
    0.37
    POSITIVE LOGITS
    endaftaran
    0.55
    IdentityProvider
    0.49
     ҳу
    0.48
    umumkan
    0.47
     comunidad
    0.47
     mağ
    0.47
     umano
    0.46
     পুলিশ
    0.46
    meldung
    0.45
     hanno
    0.45
    Act Density 0.006%

    No Known Activations