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

    Neuronpedia

    INDEX
    Explanations

    truly interactive profitable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    after
    0.40
     ect
    0.40
     Lastly
    0.39
     MEX
    0.39
     fixed
    0.38
     East
    0.38
     endlich
    0.38
     old
    0.37
     recent
    0.37
    information
    0.37
    POSITIVE LOGITS
     muchísimo
    0.46
     banane
    0.42
     সকলকে
    0.41
     smoothie
    0.40
     بسیاری
    0.39
     самостоя
    0.39
     ingrédients
    0.38
    🍐
    0.38
     く
    0.38
     هست
    0.38
    Act Density 0.003%

    No Known Activations