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

    Neuronpedia

    INDEX
    Explanations

    brave adventures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uważ
    0.42
     napp
    0.41
    নতুন
    0.41
     turpentine
    0.40
     новых
    0.38
     believers
    0.38
    与其他
    0.37
    ėmis
    0.37
    épend
    0.37
     smoothies
    0.37
    POSITIVE LOGITS
     sizeable
    0.42
     sizable
    0.39
     substantial
    0.38
    ស្ថានភាព
    0.37
    >$
    0.36
    _
    0.35
     c
    0.34
     auth
    0.34
     '('
    0.34
    击
    0.34
    Act Density 0.007%

    No Known Activations