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

    Neuronpedia

    INDEX
    Explanations

    scientific / technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xung
    -0.07
    删除
    -0.07
    чет
    -0.06
    .types
    -0.06
    fg
    -0.06
    urple
    -0.06
     tuto
    -0.06
    _share
    -0.06
     splits
    -0.06
     Dest
    -0.06
    POSITIVE LOGITS
     từng
    0.07
     Afghan
    0.06
     ATK
    0.06
     recharge
    0.06
     объек
    0.06
    Limit
    0.06
     visite
    0.06
    _MetadataUsageId
    0.06
    Senator
    0.06
     accompanied
    0.06
    Act Density 0.417%

    No Known Activations