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

    Neuronpedia

    INDEX
    Explanations

    string types in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    硙
    0.80
     المرحله
    0.79
    Small
    0.78
     والث
    0.77
    verhalten
    0.77
    کم
    0.77
    芍
    0.77
    成員
    0.77
     تلوار
    0.75
     والت
    0.75
    POSITIVE LOGITS
    []
    0.84
     prioritization
    0.78
    itized
    0.76
    ous
    0.74
    |
    0.74
     уте
    0.74
     reac
    0.74
     primacy
    0.71
     categorize
    0.70
     |
    0.70
    Act Density 0.195%

    No Known Activations