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

    Neuronpedia

    INDEX
    Explanations

    don't skip, guess, or waste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voidaan
    0.41
    tsd
    0.37
    lymph
    0.37
    resi
    0.37
     euismod
    0.37
    fø
    0.36
    fib
    0.36
    ceph
    0.36
    oph
    0.35
    MPH
    0.35
    POSITIVE LOGITS
    目標
    0.44
    ﾁ
    0.43
    人數
    0.42
     defaultConfig
    0.41
    ച്ചത്
    0.41
     aventure
    0.41
    이니까
    0.40
     controversies
    0.40
     atrap
    0.40
     eyeballs
    0.40
    Act Density 0.025%

    No Known Activations