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

    Neuronpedia

    INDEX
    Explanations

    model names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Searle
    0.42
    SKAction
    0.41
     bestowed
    0.40
    AVG
    0.38
     मुकेश
    0.37
     neutrinos
    0.37
    Almost
    0.37
     bestow
    0.37
     ดิ
    0.36
     পাশ্চাত্য
    0.36
    POSITIVE LOGITS
     Model
    0.78
     модель
    0.77
     model
    0.77
     Models
    0.75
    Model
    0.74
     मॉडल
    0.74
    Models
    0.73
    모델
    0.72
     모델
    0.72
    モデル
    0.71
    Act Density 0.003%

    No Known Activations