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

    Neuronpedia

    INDEX
    Explanations

    Return on Assets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vegan
    0.36
    ümler
    0.35
    માં
    0.35
    رهای
    0.35
    iliśmy
    0.34
    পালের
    0.34
    src
    0.33
    çok
    0.33
    üml
    0.33
    itute
    0.33
    POSITIVE LOGITS
    ารย์
    0.27
     Recordings
    0.26
     R
    0.26
     r
    0.26
     yell
    0.25
     not
    0.24
     그러니까
    0.24
     Scissors
    0.24
     Exceptions
    0.24
     rat
    0.24
    Act Density 0.000%

    No Known Activations