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

    Neuronpedia

    INDEX
    Explanations

    used to, rules, existed, Year end, driven by, Customer Management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    以及
    0.47
    Repartition
    0.45
    度和
    0.45
    玛
    0.45
    主义
    0.45
    Ethoxy
    0.44
    ToEnd
    0.44
    Recipient
    0.44
    Entities
    0.43
    Inicial
    0.42
    POSITIVE LOGITS
     Ju
    0.46
     Damages
    0.44
     costumbres
    0.43
     JU
    0.41
     s
    0.40
    miR
    0.40
     GeoNames
    0.40
     sir
    0.40
     damages
    0.40
     Customs
    0.40
    Act Density 0.001%

    No Known Activations