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

    Neuronpedia

    INDEX
    Explanations

    language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MEC
    0.44
     mec
    0.44
    DK
    0.41
     త
    0.40
    mec
    0.40
    Methyl
    0.40
     الب
    0.39
     கார
    0.39
    BK
    0.39
     spoiled
    0.38
    POSITIVE LOGITS
     models
    0.59
     model
    0.57
     modelo
    0.57
     मॉडल
    0.55
     Modell
    0.55
    models
    0.55
     Models
    0.54
     Model
    0.53
    模型
    0.53
    モデル
    0.53
    Act Density 0.044%

    No Known Activations