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

    Neuronpedia

    INDEX
    Explanations

    understand straightforwardly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     her
    0.47
     phyt
    0.43
     hemp
    0.39
    0.39
     condiment
    0.39
     তা
    0.39
     steel
    0.38
     radiology
    0.38
     MA
    0.38
     an
    0.38
    POSITIVE LOGITS
    宓
    0.54
    ಿನಿ
    0.50
    Adresse
    0.49
     Decreto
    0.47
    면
    0.46
     زاويه
    0.45
     confronts
    0.45
    冦
    0.45
    Genero
    0.45
    รุ่น
    0.45
    Act Density 0.001%

    No Known Activations