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

    Neuronpedia

    INDEX
    Explanations

    concepts and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appunto
    0.42
     mittlerweile
    0.41
     ഇത്
    0.39
    ضا
    0.39
     inn
    0.36
     inzwischen
    0.36
     Verma
    0.35
     basis
    0.35
    ськ
    0.35
    beatable
    0.35
    POSITIVE LOGITS
     abound
    0.54
    很重要
    0.54
    方面
    0.50
     Concepts
    0.46
     desempen
    0.46
     역할을
    0.46
     পরিবর্তে
    0.46
     개념
    0.45
     spielt
    0.44
     играет
    0.44
    Act Density 0.032%

    No Known Activations