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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     മനസ
    0.52
    全新的
    0.49
     Knit
    0.49
    全新
    0.46
     hardworking
    0.45
     quiero
    0.44
     ஹைட்
    0.43
     hiszen
    0.43
     දැන්
    0.43
     ব্যবহারে
    0.43
    POSITIVE LOGITS
     Wikipedia
    0.83
    Wikipedia
    0.81
     Wikimedia
    0.69
     wikipedia
    0.64
     Vikipedi
    0.64
    disamb
    0.64
     disamb
    0.64
    Wikimedia
    0.61
    Wiki
    0.60
    ː
    0.59
    Act Density 0.071%

    No Known Activations