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

    Neuronpedia

    INDEX
    Explanations

    language processing libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    1.70
    に
    1.53
    ある
    1.47
    ClN
    1.41
    ர்ஸ்
    1.40
    ములో
    1.38
    ين
    1.35
    是最
    1.34
    是很
    1.34
    ش
    1.32
    POSITIVE LOGITS
    $)$.
    1.34
    1.33
    ’
    1.27
     don
    1.22
    )’
    1.22
     recast
    1.20
     February
    1.17
     mermaid
    1.17
     truthfully
    1.16
    blätter
    1.16
    Act Density 0.123%

    No Known Activations