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

    Neuronpedia

    INDEX
    Explanations

    creative content generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     downsides
    0.45
    opausal
    0.44
     ferries
    0.41
     deaktiv
    0.40
     prohibitions
    0.39
     trainer
    0.39
     பட்டியலில்
    0.39
     governments
    0.39
     deterred
    0.39
    two
    0.38
    POSITIVE LOGITS
     creativity
    0.92
     creatividad
    0.91
     creative
    0.88
     kreativ
    0.87
     creatively
    0.86
    创造
    0.86
     creativa
    0.83
     artistry
    0.82
     Creativity
    0.82
    创意
    0.77
    Act Density 0.307%

    No Known Activations