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

    Neuronpedia

    INDEX
    Explanations

    creative writing and collaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鷹
    0.45
    т
    0.42
     creada
    0.42
    тура
    0.42
    괌
    0.41
    ж
    0.41
     स्थिति
    0.40
     חו
    0.40
    election
    0.40
     CharPtr
    0.40
    POSITIVE LOGITS
     geniuses
    0.58
     genius
    0.57
     creatively
    0.57
     creatividad
    0.57
     creativity
    0.55
     creative
    0.54
     juices
    0.54
    Creative
    0.54
     kreativ
    0.52
     Creative
    0.52
    Act Density 0.004%

    No Known Activations