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

    Neuronpedia

    INDEX
    Explanations

    & and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aceans
    0.25
     Zagre
    0.24
    缠
    0.23
     יכול
    0.23
    akon
    0.22
    Ṭ
    0.22
    étude
    0.22
    Aligned
    0.22
     equivalently
    0.22
     КА
    0.22
    POSITIVE LOGITS
     meninggal
    0.22
     byli
    0.22
     partner
    0.22
     berusia
    0.22
     partenaire
    0.22
     partners
    0.22
     gevonden
    0.22
     Associates
    0.21
     parceria
    0.21
     ristrutt
    0.21
    Act Density 0.007%

    No Known Activations