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

    Neuronpedia

    INDEX
    Explanations

    language, technical terms, and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avgsalary
    0.36
    ാൻഡ്
    0.36
     entsprechende
    0.36
     नाट्य
    0.36
    蚬
    0.36
    तोंडा
    0.36
    ával
    0.35
    mäß
    0.34
    荭
    0.34
    alertDialog
    0.34
    POSITIVE LOGITS
    .
    0.38
    ?
    0.35
     Traditional
    0.33
     finns
    0.33
     Backpack
    0.33
     forskellige
    0.33
    ,
    0.33
     extraordinaire
    0.33
     Minimal
    0.32
     newbies
    0.32
    Act Density 0.067%

    No Known Activations