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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     temples
    0.43
     इतिहासकारों
    0.38
     pens
    0.36
    Pens
    0.36
     cleanse
    0.36
     hog
    0.36
     etch
    0.35
    விடும்
    0.35
     Kitt
    0.35
     Bronze
    0.35
    POSITIVE LOGITS
    ０
    0.42
     veinte
    0.40
    ៧
    0.40
    nin
    0.40
    mtext
    0.39
     treinta
    0.39
    nim
    0.38
    ۲۰
    0.38
    １
    0.38
     ninety
    0.38
    Act Density 0.001%

    No Known Activations